Transform Condition Data into Production Insights
If it can be measured, Datanomix can detect it, guardband it, and help keep your machines running optimally. Our anomaly detection algorithms establish automatic thresholds for normal operation and alert you when conditions are out of bounds. Datanomix works with any IO-Link based sensor and seamlessly integrates this parametric data into your existing Datanomix machine view.
Ensure Optimum Conditions
Temperature, pressure, and vibration are usually leading indicators that something in your environment has changed that might impact quality. Connect new sensors, or take advantage of the ones you already have, and let Datanomix handle part-specific outlier detection automatically.
There’s nothing worse than getting a job started only to have to deal with a routine maintenance issue 60 minutes later. Our pre-packaged maintenance condition kits deal with a lot of the common challenges around maintenance. From clogged filters to misbehaving bar feeders, we have you covered.
Taking advantage of high frequency sensors and advanced signal processing, our Predictive Quality detection observes production runs looking for part-to-part variances. We’ll flag any parts that are suspect, along with the associated signals, so you can see the what, when, and why of scrap, and can build a plan to reduce it.
Conditional Monitoring FAQ’s
In addition to the alarms available from your machines themselves, you can monitor any environmental condition of your choosing. Common applications include temperatures, pressures, and vibrations.
We work with any brand of sensors that supports IO-Link. This includes the most common industrial brands such as Baluff and IFM.
We support text and e-mail alerting. Additionally, our software automatically determines reasonable statistical ranges for any condition on a per machine and per job basis. This means we know acceptable ranges of tool loads, vibrations, etc. on each job you run, and are able to guardband those to detect outliers and alert you accordingly.