The Path from Data to Actionable Information as a Driver for the Industrial Ecosystem
DATA ENRICHMENT
This stage relates the semantics to the process and use of the equipment. This is where we introduce the intention of the processes, in discrete manufacturing this is done by providing the device constraints, process plans with expected parameters and expected performance. The process constraints allow the analytics to annotate the information stream by comparing the actuals with the expectations and then reporting deviations.
Value is emergent at this stage by using technology such as Complex Event Processing 13( CEP) to recognize patterns. Since we know the meaning of the data, it is possible to place constraints on the data – for example, if the load exceeds a threshold
Enrichment can also make use of existing learning models. Once the semantics are present, it is much easier to build classification systems that provide more tangible value to the users using statistical analysis. Closed loop feedback can also be performed to alter or correct a process before damage or loss occurs.
Enrichment may also introduce additional information models; these are often static models that describe the expectations for the execution of a process and information relating to the localized process verification 14. These additional information models allow the analytics at this early stage to gain a larger perspective and make judgments about the outcome and the operation of the equipment.
Figure 3: Comparison of simulated data for part build generated by Mastercam compared to actual machine data. Note: The X- position of each dataset has been translated for ease of comparison. The vertical scales are consistent with both datasets.
when a tool is being used to cut a specific type of material, then create an event that indicates something may be going wrong.
Figure 3 illustrates the engineering predictions regarding a manufacturing
13 https:// en. wikipedia. org / wiki / Complex _ event _ processing
14
Brandl, Dennis. 2008. " T061 _ isa95-04. pdf." 05 19. https:// apsom. org / docs / T061 _ isa95-04. pdf.
- 28- June 2018