Internet of Things Sensing Networks, Deep Learning-enabled Smart Process Planning, and Big Data-driven Innovation in Cyber-Physical System-based Manufacturing.

• Date: 01 June 2020
• Author: Connolly-Barker, Melissa

1. Introduction

   As a factory eventually is highly automated, an essential component of an operational life-cycle is physical asset management. (Lee et al., 2020) Deep learning methods can identify iterative multiple assembly processes (Dusmanescu et al., 2016) and assess their operating times. (Chen et al., 2020)

2. Conceptual Framework and Literature Review

   With the harnessing of Internet of Things and big data technology, the procurement of demand (Drennan-Stevenson, 2019; Kliestik et al., 2020; Lazaroiu et al., 2020; Nica, 2015; Popescu et al., 2019; Tooby, 2019) turns out to be more coherent, convenient, and swift. (Feng et al., 2020) Because of operational barriers in a realistic production environment (Andrei et al., 2016a, b; Plumpton, 2019; Reicher, 2019), it may be challenging to collect massive quantities of data (Andrei et al., 2020; Gutschow, 2019; Lazaroiu et al., 2017; Popescu et al., 2017a, b; Rueda Garrido, 2019) for deep learning network training and enhancement. (Xiong et al., 2020)

3. Methodology and Empirical Analysis

   Using and replicating data from Capgemini, CompTIA, EY, Microsoft, PAC, and PwC, we performed analyses and made estimates regarding the relationship between Internet of Things sensing networks, deep learning-enabled smart process planning, and big data-driven innovation. Data were analyzed using structural equation modeling.

4. Results and Discussion

   Industrial Internet of Things in the development of enterprises approaches the next level so as to detect and monitor the operations of their wireless devices (Rathee et al., 2020), networking smart physical objects to each other and enabling elaborate equipment units to have incorporated sensors and particular modules (Krizanova et al., 2019; Majerova et al., 2020) that configure the link to the controlling center. (Ferrer, 2020) (Tables 1-9)

5. Conclusions and Implications

   Big data analytics is relevant in various industrial sectors because of its capacity to transform massive volumes of information into knowledge for judicious business and operational decisions. (Tao et al., 2020) Cloud manufacturing enables the harnessing of machine learning and big data technologies instantaneously, decreasing the expenses of implementing and deployment. (Morariu et al., 2020) The applications of digital twin models deal with smart manufacturing systems. (Sun et al., 2020)

   Survey method

   The interviews were conducted online and data were weighted by five variables (age, race/ethnicity, gender, education, and geographic region) using the Census Bureau's American Community Survey to reflect reliably and accurately the demographic composition of the United States. Sampling errors and test of statistical significance take into account the effect of weighting. Stratified sampling methods were used and weights were trimmed not to exceed 3. Average margins of error, at the 95% confidence level, are +/-2%. For tabulation purposes, percentage points are rounded to the nearest whole number. The precision of the online polls was measured using a Bayesian credibility interval. An Internet-based survey software program was utilized for the delivery and collection of responses.

   Data and materials availability

   All research mentioned has been published and data is available from respective outlets.

   Funding

   This paper was supported by Grant GE-1937571 from the Cognitive Automation Research Unit, New Haven, CT.

   Author contributions

   All authors listed have made a...