The control problems of complex physical systems have wide applications in science and engineering. Several previous works have demonstrated that generative control methods based on diffusion models have significant advantages for solving these problems. However, existing generative control methods face challenges in handling closed-loop control, which is an inherent constraint for effective control of complex physical systems. In this paper, we propose a C losed-L oop Diff usion method for Phy sical systems Con trol (CL-DiffPhyCon). By adopting an asynchronous denoising schedule for different time steps, CL-DiffPhyCon generates control signals conditioned on real-time feedback from the environment. Thus, CL-DiffPhyCon is able to speed up diffusion control methods in a closed-loop framework. We evaluate CL-DiffPhyCon on the 1D Burgers' equation control and 2D incompressible fluid control tasks. The results demonstrate that CL-DiffPhyCon achieves notable control performance with significant sampling acceleration. The control problem of complex physical systems is a critical area of study that involves optimizing a sequence of control actions to achieve specific objectives. It has important applications across a wide range of science and engineering fields, including fluid control (V erma et al., 2018), plasma control (Degrave et al., 2022), and particle dynamics control (Reyes Garza et al., 2023). The challenge in controlling such systems arises from their high-dimensional, highly nonlinear, and stochastic characteristics. Therefore, to achieve effective performance, there is an inherent requirement of closed-loop control.

Physics-Informed Neural Networks (PINNs) are a powerful tool for simulating complex physical systems. Unlike traditional machine learning models, PINNs can effectively utilize limited data by incorporating the underlying physics of the studied system. In scientific and engineering applications, acquiring large labeled datasets can be difficult due to the high cost and limited experimental or simulated data availability. Traditional machine learning models, such as decision trees or support vector machines, require large amounts of labeled data for effective training. However, PINNs can leverage the governing laws and constraints of the studied problem to achieve accurate results with minimal training data.

Abstract: Industrial Internet of Things (IoT) systems increasingly rely on wireless communication standards. In a common industrial scenario, indoor wireless IoT devices communicate with access points to deliver data collected from industrial sensors, robots and factory machines. Due to static or quasi-static locations of IoT devices and access points, historical observations of IoT device channel conditions provide a possibility to precisely identify the device without observing its traditional identifiers (e.g., MAC or IP address). Such device identification methods based on wireless fingerprinting gained increased attention lately as an additional cyber-security mechanism for critical IoT infrastructures. In this paper, we perform a systematic study of a large class of machine learning algorithms for device identification using wireless fingerprints for the most popular cellular and Wi-Fi IoT technologies.

While 3D printing soft materials, such as silicone or proteins, offers many advantages, it also introduces many new and complicated variables to consider when creating a new part. The existing soft materials that can be 3D printed commercially are somewhat limited since they don't have all the properties that researchers need to fully advance their developments and they end up working within the constraints of the current technology. One of the main problems with 3D printing a soft material is that it tends to deform under the forces that normally occur, sometimes even during the build, so they require support materials. According to researchers from the College of Engineering at Carnegie Mellon University, that means that additive manufacturing of soft materials requires optimization of printable inks, formulations of these feedstocks, and complex printing processes that must balance a large number of disparate but highly correlated variables (such as metal powder particle size, melt pool shape and size or filament feeding rate, extrusion width, linear plotting speed and layer thickness or suspension viscosity). Due to the critical need for integrated methodologies, they have come up with a hierarchical machine learning (HML) algorithm that optimizes parameters of these type of materials for 3D printing, using Freeform Reversible Embedding (FRE)–a recently developed method for 3D printing of liquid polymer precursors that involves controlled deposition of a fluid precursor into a supporting aqueous bath.