In this paper, we focus on the issue of adaptive fuzzy finite-time tracking control for a class of uncertain fractional-order nonlinear systems with external disturbance. A new finite-time fractional-order command filtered implementation scheme is presented for the adaptive backstepping method. In the command filtered implementation approach, analytical computation of the fractional derivatives of the stabilizing functions is not necessary. Therefore, the controller and adaptive law of the systems are easier to derive and implement. Based on the proposed command filter, adaptive backstepping technique and fractional Lyapunov’s direct method, a novel adaptive fuzzy finite-time controller is designed, which can guarantee that the tracking error converges to a small neighborhood of the origin in finite time, and other signals of the closed-loop systems are semi-global uniform ultimate bounded. In the design process of the controller, fuzzy logic systems (FLSs) are employed to approximate the unknown nonlinear functions, and an auxiliary function is adopted to compensate for the unknown external disturbance and approximation errors of FLSs. Finally, a simulation example is given to show the effectiveness and availability of the proposed control strategy.

To maintain pipeline transportation’s optimal efficiency and safety, pipelines must be regularly inspected and cleaned by the pipeline inspection gauge (PIG). Since the PIG passes through the whole pipeline, which is generally tens of kilometers, observing where the PIG is working in real-time is necessary. When the PIG passes through the pipe joint, the vibration signal will generate by the collision between the PIG and the girth weld, which can transmit along the fiber cable besides the pipeline. In this paper, we demonstrate that the optical fiber distributed acoustic sensing (DAS) can acquire the collision vibration in terms of the V pattern in the waterfall diagram, whose vertex is the collision position of PIG. The vertex will not exist when the cable positions are far away from the pipeline, which is relatively common in practice. We proposed an algorithm based on the clustering algorithm and the Hough transform to detect the position of the PIG even when the vertex of the V pattern does not exist. A field experiment shows that the proposed positioning algorithms applied to the DAS can effectively track the PIG online.

Larger-scale stochastic power systems urge the development of real-time alternating current optimal power flow, artificial intelligence (AI) thus becomes an alternative. However, traditional AI only imitates experiences, and cannot follow in-depth physics. This may cause an undesired nongeneralizability and topology intractability. To address this issue, a physics-guided graph neutral network (PG-GNN) is proposed. The PG-GNN firstly capture the physical constraints by a dual Lagrangian. Besides, the branch features of power grids are fully exploited to allow the PG-GNN to master tremendous topological patterns. To further manage the out-of-distribution topology, stability property of the PG-GNN is proved, then upon this evidence, an online transfer learning is proposed to allow the PG-GNN to fast master the unexpected topology. Numerical tests on benchmarks show that, the proposed method holds well topology-transferability, enables near or even better solutions than conventional optimizer, but merits much more than 100 times efficiency.

Recently, Industry 4.0 has attracted much attention. It has close relations with the Internet of Things (IoT). On the other hand, convolutional neural networks (CNNs) have shown promising performance in many foundational services of the IoT applications. For the IoT applications with high-speed data streams and the requirement of time-sensitive actions, fast processing is demanded on small-scale platforms or even on IoT devices themselves. Therefore, it is inappropriate to employ cumbersome CNNs in IoT applications, making the study of model compression necessary. In knowledge transfer, it is common to employ a deep, well-trained network, called teacher, to guide a shallow, untrained network, called student, to have better performance. Previous works have made many attempts to transfer single-scale knowledge from teacher to student, leading to degradation of generalization ability. In this article, we introduce multiscale representations to knowledge transfer, which facilitates the generalization ability of student. We divide student and teacher into several stages. Student learns from multiscale knowledge provided by teacher at the end of each stage. Extensive experiments demonstrate the effectiveness of our proposed method both on image classification and on single image super-resolution. The huge performance gap between student and teacher is significantly narrowed down by our proposed method, making student suitable for IoT applications.