The opaque nature of black-box deep learning (DL) models poses significant challenges for intrusion detection systems (IDSs) in Internet of Things (IoT) networks, where transparency, trust, and operational reliability are critical. Although explainable artificial intelligence (XAI) has been increasingly adopted to enhance interpretability, its impact on detection performance and computational efficiency in resource-constrained IoT environments remains insufficiently understood. This systematic review investigates the performance of an explainable deep learning-based IDS for IoT networks by analyzing trade-offs among detection accuracy, computational overhead, and explanation quality. Following the PRISMA methodology, 129 peer-reviewed studies published between 2018 and 2025 are systematically analyzed to address key research questions related to XAI technique trade-offs, deep learning architecture performance, post-deployment XAI evaluation practices, and deployment bottlenecks. The findings reveal a pronounced imbalance in existing approaches, where high detection accuracy is often achieved at the expense of computational efficiency and rigorous explainability evaluation, limiting practical deployment on IoT edge devices. To address these gaps, this review proposes two conceptual contributions: (i) an XAI evaluation framework that standardizes post-deployment evaluation categories for explainability, and (ii) the Unified Explainable IDS Evaluation Framework (UXIEF), which models the fundamental trilemma between detection performance, resource efficiency, and explanation quality in IoT IDSs. By systematically highlighting performance–efficiency gaps, methodological shortcomings, and practical deployment challenges, this review provides a structured foundation and actionable insights for the development of trustworthy, efficient, and deployable explainable IDS solutions in IoT ecosystems.
1 September 2019 in Journal of Applied Fluid Mechanics
Pigging is a common operation in the oil and gas industry. Because of the compressibility of the gas, starting up a pipeline inspection gauge (pig) from a stoppage can generate a very high speed of the pig, which is dangerous to the pipe and the pig itself. Understanding the maximum speed a pig achieves in the restarting process would contribute to pig design and safe pigging. This paper presents the modeling of a pig restarting from a stoppage in gas pipeline. In the model, the transient equations of gas flow are solved by method of characteristics (MOC). Runge‐Kutta method is used for solving the pig speed equation. The process of a pig restarting from a stoppage in a horizontal gas pipe is simulated. The results indicate that the maximum speed a pig achieves from a stoppage is primarily determined by the pressure of the pipe and the pressure change caused by the obstructions. Furthermore, response surface methodology (RSM) is used to study the maximum speed of pig. An empirical formula is present to predict the maximum speed of a pig restarting from a stoppage in gas pipeline.
15 July 2020 in Mathematical Problems in Engineering
The pipeline inspection gauge (PIG, lowercase pig is commonly used) with a bypass valve is widely used in pipeline inspection because it operates at a low speed without reducing the flow rate. Understanding the dynamics of a bypass pig in a gas pipeline would contribute to the design of the pig and the control of pig speed. This paper deals with the dynamic model for the process of a bypass pig travelling through a hilly gas pipeline. The method of characteristics (MOC) is used to solve the equations of unsteady gas flow. The backward flow of the gas in the bypass valve and pipe is shown by a simulation of pigging for a hilly gas pipeline. Parametric sensitivity analysis of pigging in the horizontal gas pipe using a bypass pig is then carried out. The results indicate that the speed of a bypass pig is most sensitive to the gas speed in the pipe followed by the bypass area and the friction of the pig. A formula, obtained from the results of the simulations using response surface methodology (RSM), is presented to predict the steady speed of a bypass pig in the horizontal gas pipeline.
Pipe cleaning is a common operation in the oil and gas industry. In this paper, the governing equation of the pipeline inspection gauge (PIG, lowercase pig is commonly used) speed is combined with the gas flow equations. The method of characteristics (MOC) is used to solve the transient equations of gas flow. And the process of a pig passing over an uphill section of a gas pipeline is simulated. The results indicate that a pig may get stuck in uphill gas pipeline, due to the coupling of the gas and the pig. Under these circumstances, a higher pressure of the upstream could be helpful for driving the pig in motion. Additionally, the ratio of inlet pressure rise during the pigging process is primarily determined by the inclination of the uphill section. In addition, a formula to predict the inlet pressure during pigging in an uphill pipe is presented. Furthermore, the proposed method and solution can be utilized to predict the speed and position of the pig, as well as the gas pressure and the stoppage of the pig in hilly gas pipelines.