Spotlight on the Industrial IoT Analytics Framework
temporarily, where the readings can be
scanned and evaluated depending on the
type of analytics. The stored values may be
discarded or archived for further
calculations. Data scientists can explore the
archived data using statistics to compute
correlations, and apply algorithms to classify
and cluster the evidence over time. Industry
subject matter experts have a good
understanding of the context and condition
of the process and assets, and can interpret
Industrial
analytics
functionality
is
deployable throughout the IIoT architecture
that is covered in the Industrial Internet
Reference Architecture (IIRA). The IIRA
addresses the need for a common
architecture framework to develop
interoperable IIoT systems for diverse
applications across a broad spectrum of
industrial verticals. The capabilities needed
for successful industrial analytics solutions
Figure 2. Analytics Mapping to the Industrial Internet Reference Architecture
are shown in Figure 2 with respect to the
other concerns in the IIRA. Each capability is
realized by a set of functions defined by use
cases that meet the stakeholders’
expectations, especially with regard to non-
functional requirements. and validate the readings and recommend
cleansing filters. It is this combination of
data science and subject matter expertise
that produces the best result
The fundamental prerequisite for industrial
analytics is availability and access to data
from the industrial process and related
assets. Data is collected close to the process
through connections and stored, at least This release of the Industrial IoT Analytics
Framework is only the beginning of a journey
to create a comprehensive study of all
aspects of how analytics can be used in the
Industrial Internet; there is still a lot of work
IIC Journal of Innovation
I N C ONCLUSION
- 39 -