Rapid advancements of artificial intelligence of things (AIoT) technology pave the way for developing a digital-twin-based remote interactive system for advanced robotic-enabled industrial automation and virtual shopping. The embedded multifunctional perception system is urged for better interaction and user experience. To realize such a system, a smart soft robotic manipulator is presented that consists of a triboelectric nanogenerator tactile (T-TENG) and length (L-TENG) sensor, as well as a poly(vinylidene fluoride) (PVDF) pyroelectric temperature sensor. With the aid of machine learning (ML) for data processing, the fusion of the T-TENG and L-TENG sensors can realize the automatic recognition of the grasped objects with the accuracy of 97.143% for 28 different shapes of objects, while the temperature distribution can also be obtained through the pyroelectric sensor. By leveraging the IoT and artificial intelligence (AI) analytics, a digital-twin-based virtual shop is successfully implemented to provide the users with real-time feedback about the details of the product. In general, by offering a more immersive experience in human-machine interactions, the proposed remote interactive system shows the great potential of being the advanced human-machine interface for the applications of the unmanned working space.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/advs.202100230

Artificial Intelligence of Things (AIoT) Enabled Virtual Shop Applications Using Self-Powered Sensor Enhanced Soft Robotic Manipulator.

Recent advances in hard-magnetic soft composites: Synthesis, characterisation, computational modelling, and applications

Magneto-actuated soft robots have broad prospects for biomedical applications, such as cell manipulation, drug delivery, and noninvasive intervention. However, the single function and unchangeable stiffness restrict their practicality. Therefore, the work presented a functionally reconfigurable soft robot based on Gallium/NdFeB/PDMS composites. A heating-free reprogrammable magnetization technique was proposed to regulate the robot's response actions through re-patterning the magnetic domains. Moreover, a stiffness programming technique in terms of the liquid-metal thermotropic phase transition was employed to regulate the robot's stiffness. Four robot prototypes were constructed and tested. Experimental results showed that the robot performed variable responses and changeable stiffness, which satisfied different manipulation tasks. Therefore, the soft robot was endowed with variable functions and reusable characteristics. The proposed technique is expected to be applied to the batch manufacturing of intelligent soft machines.

Liquid-Metal Magnetic Soft Robot With Reprogrammable Magnetization and Stiffness

Curvature impacts physical properties across multiple length scales, ranging from the macroscopic scale, where the shape and size vary drastically with the curvature, to the nanoscale at interfaces and inhomogeneities in materials with structural, chemical, electronic, and magnetic short-range order. In quantum materials, where correlations, entanglement, and topology dominate, the curvature opens the path to novel characteristics and phenomena that have recently emerged and could have a dramatic impact on future fundamental and applied studies of materials. Particularly, magnetic systems hosting non-collinear and topological states and 3D magnetic nanostructures strongly benefit from treating curvature as a new design parameter to explore prospective applications in the magnetic field and stress sensing, microrobotics, and information processing and storage. This Perspective gives an overview of recent progress in synthesis, theory, and characterization studies and discusses future directions, challenges, and application potential of the harnessing curvature for 3D nanomagnetism.

/pdf/magnetism-in-curved-geometries-3g9p8gk6b4.pdf

Magnetism in curved geometries

/pdf/magnetic-actuation-methods-in-bio-soft-robotics-yuls63w75e.pdf

Magnetic Actuation Methods in Bio/Soft Robotics

Recently, Internet of things (IoT) devices have been widely implemented and technologically advanced in manufacturing settings to monitor, collect, exchange, analyze, and deliver data. However, this transition has increased the risk of cyber-attacks, exponentially. Subsequently, developing effective intrusion detection systems based on deep learning algorithms has proven to become a reliable intelligence tool to protect Industrial IoT devices against cyber threats. This paper presents the implementation of two different classifications and detection utilizing the long short-term memory (LSTM) architecture to address cybersecurity concerns on three benchmark industrial IoT datasets (BoT-IoT, UNSW-NB15, and TON-IoT) which take advantage of various deep learning algorithms. An overall analysis of the performance of the proposed models is provided. Augmenting the LSTM with convolutional neural network (CNN) and fully convolutional neural network (FCN) achieves state-of-the-art performance in detecting cybersecurity threats. 

/pdf/a-novel-fully-convolutional-neural-network-approach-for-12rssgyz.pdf

A novel fully convolutional neural network approach for detection and classification of attacks on industrial IoT devices in smart manufacturing systems

A deep hybrid learning model for detection of cyber attacks in industrial IoT devices

Resource scheduling in cloud-based manufacturing system: a comprehensive survey

Manufacturing systems have become progressively complex and costly. Competition and the drive for profits are forcing companies to improve productivity in their production lines through effective and proper methods of evaluating production schedules. Computer simulation is one of the reliable and well-established methods that enables companies to evaluate their line scheduling. It helps manufacturers detect and rectify the line problems and move forward with productivity improvements. The main contribution of this paper is threefold. First, it defines a computer-based framework for modeling and simulation of production schedule using real-world data collected in an eyeglasses production factory. Second, it investigates an experimental conformance verification, i.e., confirming whether the simulation carried out in the production line conforms to its intended specification or not. Therefore, the simulation results are verified by the experimental results obtained from the line. Based on the confirmed simulation study, the Generating station and Washing station are considered the line’s bottlenecks. Third, it proposes some suggestions by introducing and using “what-if” analysis. Creating “What-If” scenarios is extremely beneficial for manufacturers as it allows them to conduct simulation runs based on demand forecasts and constraint modeling for generating various iterations of the production schedule. Here, different scenarios are compared and the most advantageous one is chosen. In this study, increasing 4 machines in the Generating station and 6 workers in the washing station propels the company to achieve higher system utilization and increased throughput rates by 25% and 46%, respectively. of the manufacturing system. In this regard, this paper reports the methodology to analyze and evaluate and improve the productivity of a manufacturing system in an eyeglasses manufacturing factory. A computer simulation model is built using ARENA software to analyze the current system and then based on existing data in the production line, the results obtained from the simulation are validated. The validated model shows that the Generating process in the Surfacing section and AR handwashing process are the bottlenecks of the production line. Then two simulation models are proposed regarding the “what if” tool. The simulation study shows that the AR-handwashing process is more critical, and it may be the main bottleneck in the production line. The proposed changes based on the simulation study result in a 25% increase in system utilization rate (from 52.3% to 76.9%) and a 46% increase in the system’s throughput (from 4057 to 5959 units). These results show that the computer simulation is a powerful tool to analyze and evaluate the productivity of a production line and can continuously improve it using the “what if” analysis methodology.

Rasoul Rashidifar

Papers

Magnetic Actuation Methods in Bio/Soft Robotics

A novel fully convolutional neural network approach for detection and classification of attacks on industrial IoT devices in smart manufacturing systems

A deep hybrid learning model for detection of cyber attacks in industrial IoT devices

Resource scheduling in cloud-based manufacturing system: a comprehensive survey

Simulation and Analysis of Production Scheduling in Eyeglasses Industry for Productivity Improvement