Search

Fracture initiation has been a challenging issue for fracturing deep and tight gas reservoirs, which generally requires a high breakdown pressure for hydraulic fracturing treatment. In this situation, fluid injections frequently have to terminate at the very beginning. Toward predicting and solving this issue, a novel fracturing system for deep and tight sandstone gas reservoirs was developed. The key components of the fracturing system and some criterion will be introduced, which can be used to optimize the ideal perforation locations along the landing part and select the right perforation strategy accordingly. The main components of the fracturing system include: (1) evaluating the log-based diagenetic rock typing and flow index; (2) 1D mechanical earth model; (3) calculating the breakdown pressure envelope along the well trajectory of the landing part; (4) calculating the optimal perforation directions along the landing part; (5) select the first set of perforation locations based on the log-based diagenetic rock typing and flow index; (6) narrowing down the first set of perforation locations to a second set of perforation locations based on the breakdown pressure envelope; (7) determining a perforation strategy based on breakdown pressure envelope and wellhead pressure safety limit in the second set of perforation locations. The computational framework to calculate the breakdown pressure envelope and optimal perforation directions is applicable to arbitrary well trajectory. The fracturing system has been used to provide pre-fracturing suggestions for wells landed in deep and tight sandstone reservoirs, which is very efficient for identifying locations with good rock typing and relatively low breakdown pressure. Also, it can indicate whether oriented perforation should be used further for alleviating breakdown issue. By taking these efforts and procedures, the fracturing success rate for deep and tight sandstone gas reservoirs can be improved, which has been verified in practice. Example studies from the field will be provided to demonstrate the fracturing system's performance and applicability.

Causal structure learning plays a crucial role in the current field of artificial intelligence, yet existing causal structure learning methods are susceptible to interference from data sample noise and often become trapped in local optima. To address these challenges, this paper introduces a continuous optimization algorithm based on the curriculum learning framework: CL-NOTEARS. The model utilizes the curriculum loss function during training as a priority evaluation metric for curriculum selection and formulates the sample learning sequence of the model through task-level curricula, thereby enhancing the model’s learning performance. A curriculum-based sample prioritization strategy is employed that dynamically adjusts the training sequence based on variations in loss function values across different samples throughout the training process. The results demonstrate a significant reduction in the impact of sample noise in the data, leading to improved model training performance.

Unmanned Aerial Vehicles (UAVs) have been widely used in localized data collection and information search. However, there are still many practical challenges in real-world operations of UAV search, such as unknown search environments. Specifically, the payoff and cost at each search point are unknown for the planner in advance, which poses a great challenge to decision making. That is, UAV search decisions should be made sequentially in an online manner thereby adapting to the unknown search environment. To this end, this paper initiates the problem of online decision making in UAV search planning, where the drone has limited energy supply as a constraint and has to make an irrevocable decision to search this area or route to the next in an online manner. To overcome the challenge of unknown search environment, a joint-planning approach is proposed, where both route selection and search decision are made in an integrated online manner. The integrated online decision is made through an online linear programming which is proved to be near-optimal, resulting in high information search revenue. Furthermore, this joint-planning approach can be favorably applied to multi-round online UAV search planning scenarios, showing a great superiority in first-mover dominance of gathering information. The effectiveness of the proposed approach is validated in a widely applied dataset, and experimental results show the superior performance of online search decision making.

The influence of the thermal conductivity of silica bricks on the coking process as an important component of the coking and combustion chambers is still unclear. A multi-chamber coupling mathematical model of a coke oven is developed to investigate the energy-saving effect of using high thermal conductivity silica bricks in the coke oven. The model is validated using measured temperatures of coal and flue gas bed in a coke oven in operation for a coking cycle. Temperature variation and its distribution in the coking chamber, combustion chamber, and heating wall are simulated for the coke oven using silica bricks with different thermal conductivities. The obtained results showed that compared with the use of common silica bricks, coking time of one cycle can be reduced by ∼60 min, with a decreased consumption of fuel gas by ∼4.9%. The enhancement of heat transfer from the flue gas to the heating wall and the heating wall to coal using silicon bricks with high thermal conductivity can effectively shorten not only the temperature difference between the two sides of the heating wall but also reduce the mean flue temperature of the flue gas by ∼24.5 °C.

Ship trajectory classification is of great significance for shipping analysis and marine security governance. However, in order to cover up their illegal fishing or espionage activities, some illicit ships will forge the ship type information in the Automatic Identification System (AIS), and this label noise will significantly impact the algorithm’s classification accuracy. Sample selection is a common and effective approach in the field of learning from noisy labels. However, most of the existing methods based on sample selection need to determine the noise rate of the data through prior means. To address these issues, we propose a noise rate adaptive learning mechanism that operates without prior conditions. This mechanism is integrated with the robust training paradigm JoCoR (joint training with co-regularization), giving rise to a noise rate adaptive learning robust training paradigm called A-JoCoR. Experimental results on real-world trajectories provided by the Danish Maritime Authority verified the effectiveness of A-JoCoR. It not only realizes the adaptive learning of the data noise rate during the training process, but also significantly improves the classification performance compared with the original method.

Critical network defense and attack problems, usually modeled as network interdiction, is of great significance. It is of great interest from the interdictor's view to study saturation property of resource allocations. This paper presents a bi-objective shortest path network interdiction model with node interdiction, in which the interdictor seeks to interdict a set of nodes in the network that is Pareto-optimal with respect to two objectives, i.e., maximization of shortest path length and minimization of resources cost. A novel subgraph sequence algorithm is developed to identify the efficient frontier through a sequence of single-objective problems. Novel subgraph decomposition algorithms are proposed to solve single-objective problems. Features and time complexity of those problems and algorithms are analyzed. Moreover, to make a trade-off between the resource investment and the interdiction performance, the definition and the computing method of saturation point are introduced in this paper. Both simulated grid network and real-world transportation network data are used to evaluate the performance of algorithms in numerical experiments. The results show that the subgraph sequence algorithm can achieve the optimal Pareto-frontier of this bi-objective problem effectively.

Event Detection (ED), which aims to identify trigger words from the given text and classify them into corresponding event types, is an important task in Natural Language Processing (NLP); it contributes to several downstream tasks and is beneficial for many real-world applications. Most of the current SOTA (state-of-the-art) models for ED are based on Graph Neural Networks (GNN). However, a few studies focus on the issue of GNN-based ED models’ robustness towards text adversarial attacks, which is a challenge in practical applications of EDs that needs to be solved urgently. In this paper, we first propose a robustness analysis framework for an ED model. Using this framework, we can evaluate the robustness of the ED model with various adversarial data. To improve the robustness of the GNN-based ED model, we propose a new multi-order distance representation method and an edge representation update method based on attention weights, then design an innovative model named A-MDL-EEGCN. Extensive experiments illustrate that the proposed model can achieve better performance than other models both on original data and various adversarial data. The comprehensive robustness analysis according to experimental results in this paper brings new insights into the evaluation and design of a robust ED model.

Network defense and attack problems can be modeled as network interdictions. In this paper, we consider a new version of the network interdiction problem that optimizes the interdictor's resource consumption while limiting network capacities (e.g., the shortest path) to a specified threshold. Interdictors would balance the interdiction performance and resource consumption when maximizing the performance costs too much. The most frequently-used technique is to relax the maximization restraint to certain specified threshold; however, the known algorithms provide little help in calculating the threshold restraint. We present a novel model named minimizing the interdiction resource with goal threshold based on the shortest path interdiction problem and propose two basic algorithms to solve it based on Benders decomposition and Lagrange duality, respectively. To consider the situation of complete interdiction and that of a large threshold, a corresponding set-covering algorithm and a Lagrange approximate algorithm are presented. Computational experiments show that decomposition-based algorithms generally perform better on small-world networks while duality-based algorithms perform better on regular grid networks. Analyses on network property sensitivity show that the decomposition-based algorithms are sensitive to the threshold value while the duality-based algorithms become weaker as the interdiction increment grows. Furthermore, we evaluate the performance of these two basic algorithms on a real-world Chicago transportation network. The result illustrates a significant advance; both algorithms can compute an optimal strategy for problems that scale up to real-world sizes.

Network security is a crucial challenge facing Internet-of-Things (IoT) systems worldwide, which leads to serious safety alarms and great economic loss. This paper studies the problem of malicious interdicting network exploitation of IoT systems that are modeled as a bi-layer logical–physical network. In this problem, a virtual attack takes place at the logical layer (the layer of Things), while the physical layer (the layer of Internet) provides concrete support for the attack. In the interdiction problem, the attacker attempts to access a target node on the logical layer with minimal communication cost, but the defender can strategically interdict some key edges on the physical layer given a certain budget of interdiction resources. This setting generalizes the classic single-layer shortest-path network interdiction problem, but brings in nonlinear objective functions, which are notoriously challenging to optimize. We reformulate the model and apply Benders decomposition process to solve this problem. A layer-mapping module is introduced to improve the decomposition algorithm and a random-search process is proposed to accelerate the convergence. Extensive numerical experiments demonstrate the computational efficiency of our methods.

Stealth malware is a representative tool of advanced persistent threat (APT) attacks, which poses an increased threat to cyber-physical systems (CPS) today. Due to the use of stealthy and evasive techniques, stealth malwares usually render conventional heavy-weight countermeasures inapplicable. Light-weight countermeasures, on the other hand, can help retard the spread of stealth malwares, but the ensuing side effects might violate the primary safety requirement of CPS. Hence, defenders need to find a balance between the gain and loss of deploying light-weight countermeasures, which normally is a challenging task. To address this challenge, we model the persistent anti-malware process as a shortest-path tree interdiction (SPTI) Stackelberg game with both static version (SSPTI) and multi-stage dynamic version (DSPTI), and safety requirements of CPS are introduced as constraints in the defender’s decision model. The attacker aims to stealthily penetrate the CPS at the lowest cost (e.g., time, effort) by selecting optimal network links to spread, while the defender aims to retard the malware epidemic as much as possible. Both games are modeled as bi-level integer programs and proved to be NP-hard. We then develop a Benders decomposition algorithm to achieve the Stackelberg equilibrium of SSPTI, and design a Model Predictive Control strategy to solve DSPTI approximately by sequentially solving an 1+δ approximation of SSPTI. Extensive experiments have been conducted by comparing proposed algorithms and strategies with existing ones on both static and dynamic performance metrics. The evaluation results demonstrate the efficiency of proposed algorithms and strategies on both simulated and real-case-based CPS networks. Furthermore, the proposed dynamic defense framework shows its advantage of achieving a balance between fail-secure ability and fail-safe ability while retarding the stealth malware propagation in CPS.