The Prognostics Company - forecasting malfunctions
Big Data & Cloud Technologies
Cassantec prognosticates the future based on data histories. The algorithms are based on a blend of AI, machine learning and Big Data and are broadly applicable. Cassantec had its commercial kick-off in the Industrie 4.0 environment: the software prognosticates the timing and probability of malfunctions of industrial assets. Hence, our prognostic approach adds an explicit future time line to established diagnostics and predictive maintenance tools. The prognostic results are used to create more efficient maintenance strategies and to reduce unforeseen downtime. Cassantec Prognostics is built on a new and unique combination of mathematical methods (Markov and Bayes, machine learning) used to calculate condition trends, risk profiles of malfunctions and remaining useful life (RUL). For the calculations, condition and process data are used and correlated to malfunctions. The results of the stochastic calculations are presented in a decision-oriented format which helps the operator to optimize necessary maintenance strategies. The interface of the software is easy and clearly structured: it contains the integration of all data, a graphical overview of all components, transparent color codes, a short description of the malfunctions and a clear overview of the RUL of the asset and its single components. Furthermore, it is interactive allowing, among others, future scenario and retrospective analyses. The reports are retrieved by the asset operator through a Cloud-based SaaS model. Benefits can be derived from the following factors:
- Early information on malfunctions lead to less downtime and less maintenance interventions
- Decreased maintenance costs through intelligent maintenance planing
- Objective information and standardized formats provide transparency, a well-grounded decision-making basis and fleet-wide benchmarking over time
- Facilitate the efficient retention of critical technical knowledge, an aspect that gains in importance due to an ageing workforce.