Effective data analysis is a key value driver in the context of Industry 4.0 and the ‘smart factory’. Big data has no significant value until the enormous amounts of data that arise in IoT environments can be effectively aggregated and analysed so that they impact on results. This may result, for example, in the fact that the data enable predictive planning and maintenance (Advanced Analytics, predictive planning and Predictive Maintenance) and thus lower operating and quality costs.
Or that processes are automated in combination with learning systems. Particular potential in this context comes from the construction of digital twins, virtual models that reproduce and interlink objects and processes completely in real time and thereby allow high transparency and accurate predictions of optimisation possibilities and risks. In addition, using Advanced Analytics tools, an enormous number of potential correlations can be tested and analysed, which allows a much deeper and more accurate understanding of the core processes.
Data analyses also provide the basis for better understanding customer requirements and decisions (and earlier), which leads to higher responsiveness and competitive advantages. Finally, intelligent products and services (smart products & services) can build up and generate additional revenues within new business models.
At the same time, value-generating data analyses often fail because the Connectivity of the elements in the network is not given, the data quality is insufficient, there are insufficient amounts of data, or the existing IT structures do not allow comprehensive, functional and inter-divisional data management. Also missing in many companies are the skills and competencies required to establish data analysis as a key cross-sectional discipline and integrate it into strategic and operational processes.
ROI has the comprehensive technical and technological expertise to support companies in the manufacturing industry in the effective and profitable use of data analytics. In doing so, we are oriented on a methodically well-founded approach which has been proven in numerous practical projects.
- Understanding data: Solution of technical issues, especially with regard to data sources and types, frequency of data collection and business-related questions in terms of significance and business value
- Collecting data: Integration of data from different data sources, collection of additional data on expansion of the solution space and selection of a representative period
- Preparing data: Structuring, duplicate cleansing, plausibility checks and handling of incomplete values and outliers (anomalies)
- Analysing data: Visualisations and descriptive analysis in combination, advanced analytics
- Creating a mathematical model: Stability and sensitivity analyses and regular validation of the forecasting quality
- Interpreting results: Information on the validity of data and avoidance of misinterpretation (correlation ≠ causality)
- Change management for implementing the changes induced by data analysis
Development of a digital twin to increase quality and productivity
An automotive supplier improved the transparency of work and organizational processes in a production plant for dashboards.
With a "Digital Process Twin" from ROI, the company reduced the reject rate and made improvement potentials in its Value creation networks visible.