The maiot asset optimization platform uses a set of tools to detect, analyse and predict events. Tailored to your assets and business needs, these tools unlock use cases like damage detection, root-cause analysis and predictive maintenance – on any form of time series data.
Learn more about success stories from our customers.
We help you find the right data and select the right tools for your use case.
Example cases we've worked on:
We connect to the data you already have, or help you record data from your assets.
We can support almost any data source:
Every insight is delivered to you – immediately, and exactly where you need it
Select the right delivery method:
In order to ensure both
viable business cases and
viable data, we work in a three-tier project system. We evaluate your data and our joint business case in a timeboxed feasibility project, integrate your data into our system and optimize our tool's results in a integration project and finally transition to a subscription plan for you to seamlessly scale.
You have a muddy data lake or an unclear business case? Do a timeboxed feasibility project with us and get definite clarity of viability.
Integrate your data and our platform for continuous transmission. Our experts will start optimizing results and validate findings.
Use the tailor-made tooling we provide with a clear-cut cost structure. Pay per connected asset and get continuous improvements of your results.
Learn more about how our customers have used the maiot platform to their benefit, and how our experts are able to help creating new business cases for you.
Through many successful projects, we were able to identify J1939 as excellent source of time series data for our platform. The standardized data format and the component-based data stream are well-suited to detection, analysis and prediction of mision-critical events.
Together with our customers, we have successfully predicted failures of air pressure systems and other mision-critical subcomponents. In addition to predictions on a subcomponent-level, we were also able to predict critical events in related business processes such as warranty claims and spare part orders.
For a customer providing maintenance services we were able to detect and predict failures in cooling machines. The highly dynamic usage patterns and environments (e.g. loading/unloading, variation of freight, external conditions) make traditional approaches like using DTCs unfeasible.
With a time horizon optimized for our customers specific business needs, the loss of freight - especially for high-value freight such as medication and cooling-chain dependent foods - could be avoided.
In multiple projects, instead of predicting failures the pure detection of damages to assets alone proved to be a game changer for our customers.
By learning from historical failures emerging threats to critical assets can be identified without constant human supervision of assets. For certain use cases without available historical insights, anomalies and damage events can even be detected from new data alone.
Furthermore, by adding root cause analysis to the recorded data stream and related damages, our customers were able to identify failure patterns within their manufacturing as well as within assets in the field - remotely, without physical access to the assets. In turn, our customers were able to optimize their manufacturing processes and could remotely diagnose previously unknown issues.
Together with our customers, we’re able to provide additional insights for research and development.
Customers were able to detect previously undetectable failures and damages in new generations of assets ahead of their market launch and could in turn fix potentially reputation-damaging and costly production flaws.
The analysis of root causes for detected failures was made possible by using our root-cause analysis, even though the observed behaviours were not backed through historic data.
Ultimately, by collaborating during the development phase, the ability to record the right data can be baked in natively into new asset generations, thus enabling predictive maintenance use cases for consumers.