B. The Advanced Manufacturing Analytics Platform
The Advanced Manufacturing Analytics Platform [7] is an integrated BI platform for holistic data-driven manufacturing process optimization. It is based on a transfer of concepts of the Deep Business Optimization Platform [8], [3], [9] to the area of manufacturing. Its conceptual architecture consists of three integrated layers sketched in Fig. 1.
The Data Integration Layer integrates process and operational
manufacturing data in a holistic processcentric
data warehouse, the Manufacturing Warehouse.
In general, operational data are subject-oriented and
represent data of traditional Data Warehouses, e. g.,
sales data. Process data are flow-oriented and comprise
execution data, i. e., events recorded during process execution,
and process model data [9]. The Manufacturing
Warehouse abstracts heterogeneous source formats and
provides a unified multidimensional view on all process
aspects. Considering data provisioning, the Manufacturing
Data Integrator matches process and operational
source data and consolidates them into the Manufacturing
Warehouse.
Various analysis techniques, esp. data mining methods
and metrics calculation, are at the heart of the Process
Analytics Layer. Generated insights, i. e., analysis results,
are stored in the Manufacturing Insight Repository
as a central component for sharing, combination and
reuse of analysis results, e. g., data mining models. It is
oriented towards the dBOP approach in [10].
The Process Optimization Layer focuses on the application
and combination of insights from the Manufacturing
Insight Repository to support the actual process improvement.
Indication-based Manufacturing Optimization
as well as Pattern-based Manufacturing Optimization
are presented in this article.