Traditionally, the structure maintenance follows an established procedure (IQOA in France for example), often it has a routine of periodical inspections, tests and repairs. In most of the case, if an issue was not spotted during the periodical inspections, the issue would be neglected.
To fully understand the structures’ health conditions, the maintenance team needs to observe and collect various measurements in both global and local perspectives. Depending on the diversity of the structures, other characters have also to be considered, such as the architecture design, the building materials, the lifespan and so on. Thus, various instrumentations and test tools are required and their measurement data need to be integrated in analysis. It is then hard to build a consistent cost-effective periodical inspection and evaluation process. The uncertainty of detecting an issue and resolve it leads to unpredictable risks on the structure health and safety.
To improve the current situation, Morphosense originate
the innovative system NEURON : Real-time continuous, synchronized,
3D deformation and 3-axis vibration monitoring.
We provide all-around static and dynamic behavior monitoring of structures. All the monitoring data is real-time, simultaneous and synchronous. Based on MORPHOSENSE key indicators, operation and maintenance team could make evaluations and decisions. Thus, the monitoring solution reduce time-lapse of detecting structure health issues, mitigate risks of structure failure, increase the efficiency and effectiveness of maintenance and lower maintenance costs.
Leverage on our system interoperability, we are able to integrate off-shelf sensors into our monitoring solution. Thereby, we are capable local monitoring for critical part of the structure by integrating constraint gauges, corrosion sensor or cracks detection, as well as overall environment context monitoring by completing weather station, camera and wave sensor into the system.
With patents algorithms, we interpret data into structure health information for making maintenance decisions. And moreover, we have invested to R&D on artificial intelligence. By applying machine learning, outlier detection, novelty detection and weak signal detection to our measurement data, we are able to understand the structure behaviors under different circumstances, recognize the unexceptional structure behaviors, identify the cause of the structure health degradation and establish proactive needed-base maintenance.