I started using I-sense and it provides all the necessary tools for my day-to-day job, inclusing vibration and spectrum analysis, battery levels monitoring, notifications of alerts, etc. I highly recommend the solution to all veterans of the field
Predictive Maintenance is a routine activity to inspect or test for the presence of warning conditions that indicate that the item is about to fail. As condition monitoring technology continues to advance we analyse current data to make predictions about the future. In its simplest form, a simple rule that says that if bearing vibration exceeds a certain value, then the bearing is about to fail is a simple form of Predictive Analytics. However much more sophisticated predictive models are possible, and it is in this area that a lot of development is occurring.
Analytics Control Panel
I-SENSE applies Machine Learning and modern optimization to preventive maintenance, offering three main areas:
Descriptive: I-SENSE constructs a Failure Modes, Effects and Critcality Analysis (FMECA) tree in a data-driven fashion. Additionally, using field expertise, the platform helps simulate real data to construct sizeable dataset that would alternatively require huge investments to collect.
Predictive: Using time series analysis of machine states, I-SENSE predicts the failure class of a given equipment, the underlying cause, future evolutions, and the potential RUL (Remaining Useful Life).
Prescriptive: I-SENSE implements a sophisticated recommendation engine able to suggest actions to take in order to correct the trajectory and minimize the average downtime of the system.
Vibration data analytics
I-sense analytics in depth works on all assets vibration data to propose real-time predictions of machine health. Multiple models are applied to yield different results and insights such as:
- A list of all possible failures with a respective probability for each failure mode
- A complete FMECA tree for the asset showing the probable cause and origin of a failure mode.
- A prescription vs model output that contrasts the predictions yielded by the model with the real output given by an expert from the field.
- An interpretability tree (for compatible models)
In-depth machine health predictions
Tailored analytics solutions
The ability to integrate multiple data architectures on I-sense allows analytics models to be based on current sensor data as well as historical data
Analytics can solve many issues in many areas, however to have an accurate model the input parameters may vary depending on the specific case to be treated for each company, we give the necessary care to build the suitable model tailored to your real case variables.
During the entire period of growth of the model, we provide you with all the necessary assistance from our data scientists for proper results.