Optimization of Manufacturing Production and Process

This chapter mainly introduces production processing optimization, especially for machining processing optimization on CNC. The sensor collects the original vibration data in time domain and converts them to the main feature vector using signal processing technologies, such as fast Fourier transform (FFT), short-time Fourier transform (STFT), and wavelet packet in the 5G AI edge computing. Subsequently, the main feature will be sent for cloud computing using genetic programming, Space Vector Machine (SVM), etc. to obtain optimization results. The optimization parameters in this work include machining spindle rotation velocity, cutting speed, and cutting depth, while, the result is the optimized main spindle rotation speed range of CNC, which met machining roughness requirements. Finally, the relationship between vibration velocity and machining quality is further studied to optimize the three operational parameters.

Radio Systems and Computing at the Edge for IoT Sensor Nodes

Many Internet of Things (IoT) applications use wireless links to communicate data back. Wireless system performance limits data rates. This data rate limit is what ultimately drives the location of computing resources—on the edge or in the cloud. To understand the limits of performance, it is instructive to look at the evolution of cellular and other radio systems. The emphasis will be on the RF front-end architectures and requirements as well as the modulation schemes used. Wireless sensor nodes will often need to run off batteries and be low-cost, and this will constrain the choice of wireless communications system. Generally cheap and power efficient radio front ends will not support high data rates which will mean that more computing will need to move to the edge. We will look at some examples to understand the choice of radio system for communication. We will also consider the use of radio in the sensor itself with a radar sensor system.

Applications of Machine Learning in Healthcare

Machine learning techniques in healthcare use the increasing amount of health data provided by the Internet of Things to improve patient outcomes. These techniques provide promising applications as well as significant challenges. The three main areas machine learning is applied to include medical imaging, natural language processing of medical documents, and genetic information. Many of these areas focus on diagnosis, detection, and prediction. A large infrastructure of medical devices currently generates data but a supporting infrastructure is oftentimes not in place to effectively utilize such data. The many different forms medical information exist in also creates some challenges in data formatting and can increase noise. We examine a brief history of machine learning, some basic knowledge regarding the techniques, and the current state of this technology in healthcare.

Remote Management of Autonomous Factory

In today’s mass production era, the world is making things (products and systems) so quickly and systematically in huge volume. The demand for these products is very high and, at the same time, consumers are still in search for a need for making the production very personalized. Hence, the “one mold fits all” approach may not seem to be enough. The present approach is facing the lack of networking between the automation pyramid levels, that is, especially between enterprise resource planning (ERP) and manufacturing execution system (MES) layers and, in turn, communicating directly with the lower layers is not possible. This missing communication among the process equipment like machineries and field control systems like PLCs at the production shop floors implies that customization at the product layer for the consumer is still in progress in classical manufacturing. Mini-MES is a new concept being introduced here to solve the existing techniques reported in the literature and is followed by industry best practices. The novel mini-MES platform provides an avenue for the technology process level (the most bottom layer) to interplay interconnectivity and interoperability with its higher levels until the above pain points are addressed holistically. The chapter is going to focus mainly on the factory production of digital manufacturing and on describing the 3-Cs implementation plan, the enabling technology, and the achievable outcome ahead.

Energy Harvesting Technology for IoT Edge Applications

The integration of energy harvesting technologies with Internet of things (IoTs) leads to the automation of building and homes. The IoT edge devices, which include end user equipment connected to the networks and interact with other networks and devices, may be located in remote locations where the main power is not available or battery replacement is not feasible. The energy harvesting technologies can reduce or eliminate the need of batteries for edge devices by using super capacitors or rechargeable batteries to recharge them in the field. The proposed chapter provides a brief discussion about possible energy harvesting technologies and their potential power densities and techniques to minimize power requirements of edge devices, so that energy harvesting solutions will be sufficient to meet the power requirements.