EAGER:Cybermanufacturing:Collaborative Research: A novel process data analytics framework for IoT-enabled cybermanufacturing

点击翻译按钮获取中文摘要

Abstract Wang/He, 1547163/1547124 (Collaborative proposal)There is general consensus that factories and plants that are connected to the internet are more efficient, productive and smarter than their non-connected counterparts. Next generation manufacturing systems are expected to include the application of increasingly powerful and low-cost computation and networked information-based technologies. Internet of Things (IoT) devices are sensors/actuators, computers with wireless networks that are small and easy to embed. IoT devices offer the opportunity to instrument systems with massive numbers of sensors. With the huge amount of data and the programmability of IoT devices, comes the opportunity to shape the data received, to address local redundancy of information, and to improve both the accuracy and precision of measurements locally and across a distributed parameter system such as a reactor.With the emergence of the IoT and ever advancing computing power and expansion of wireless networking technologies, a new generation of networked, information-based technologies, data analytics, and predictive modeling are providing new embedded computing capabilities as well as access to previously unimagined potential uses of data and information. These capabilities provide possibilities for new, radically better ways of doing manufacturing. As noted in Advanced Manufacturing Partnership 2.0 (AMP 2.0), if potential faults and failures are detected and corrected while still incipient, reduction of plant downtimes of 50% in five years and 90% in ten years may be achieved. Converting these possibilities into reality remains challenging. In this EAGER proposal, the PIs propose a new process data analytics framework with the aim of providing smart diagnostics and prognostics for cybermanufacturing. As part of this effort, they also propose to establish an IoT-enabled manufacturing technology testbed (MTT) to explore and establish a proof-of-concept for the proposed framework.The PIs propose a statistics pattern based process monitoring (SPPM) framework as one of the potential solutions. This SPPM will make use of the higher order statistics of process variables that have not been utilized before to directly quantify the process nonlinearity and nonnormality. In addition, a Bayesian-based event classification is proposed to enable intelligent, self-adaptive modeling, a key capability of cybermanufacturing system monitoring. By establishing an IoT enabled manufacturing technology testbed and running designed experiments, this project should yield a better understanding of the properties, capacities and performances of IoT devices. If successful, this project will create one of the first prototypes of the 3rd generation statistical process monitoring methods. The idea of the proposed statistics pattern based data analytics is not limited to process monitoring. It provides a modeling framework that can be applied for process/product design and predictive maintenance by relating cybermanufacturing Big Data to different objectives.