Large amounts of data are being collected for regulation and monitoring of technical facilities. This data is in many ways connected to energy efficiency of the facility. Our energy effiency module unleashes potential energy and CO2 savings through high precision data analysis. The use of available data avoids new expensive measurements and keeps the costs low.
- Does the replacement of an aggregate yield enough energy savings to justify the additional costs?
- How much energy will a pump with variable operating points consume during the next year?
- Does the suboptimal configuration of components cause an energy loss?
- Does the dimensioning of parts correspond to the conditions of the actual process?
Whether the purchase of a machine will be profitable depends highly on the expected operating conditions. In reality however, these conditions are influenced by many different factors, which leads to a complex distribution of operating points. The Investment Module can calculate the Net Present Value of an investment, by predicting the operating points accurately.
- Is the replacement of a machine worth the expense, considering the changed operating conditions?
- How can investment in plant construction be optimized through Life-Cycle-Costs forecasts?
- When does an investment reach the point of maximum rentability?
- Which machine is less expensive in the long run?
Maintenance decisions are influenced by many factors, that are already recorded either directly or indirectly. Thus, the analysis of existing sensor data can contribute to an improvement of maintenance cycles and failure prediction at an early stage. But the Maintenance Module reaches much further than a target vs. actual comparison. In fact, its precise analysis allows the distinction between noise and systematic changes. Furthermore, it can recognize the interrelations between slight sporadic deviations and malfunctions.
- Can the anticipated replacement of a machine prevent its breakdown?
- How can the engineer decide based on sensor data whether a machine is actually defective or the sensor only provides faulty information?
- What is the risk of breakdown of a component according to the current sensor information?
- How do temperature fluctuations and high throughput periods influence the maintenance schedule?
- Could additional facility monitoring reduce maintenance cost significantly?
Data in various business areas contain timestamps, which are recorded in different business processes as the date of events or realtime measurements in milliseconds. The problem with these data lies in the noise that can be caused by random delays overlaying the captured events. Further, important information can be concealed in different frequencies. The Timeseries-Module solves theses problems in order to answer your questions.
- Which completion date is realistic?
- How can personnel planning be coordinated, according to actual occupancy rates at cash registers?
- Which is the shortest processing duration that can be achieved in the best case?
- When is a product definitely completed?