sensorless predictive analytics.

Supercharge your predictive analytics with high-frequency machine data. Diagnose, predict, and avoid failures with unprecedented visibility into the condition of your equipment with no sensors required.

Gain unprecedented fidelity with plug-and-play high frequency data collection.
mm20_icon_R2_health predictive
Leverage transformed data to immediately  identify problems never visible before.
mm20_icon_R2_health preventative
Deliver solutions on the edge to stop problems before they cause expensive downtime.
It is a messy, tedious activity to acquire, parse, and clean data for analysis in a factory.
  • When tools break, it can be costly.
  • A damaged tool can still make parts that seem to spec, but end up often getting scrapped.
  • Subtle anomalies in machine load, torque, acceleration, and spindle speed can cause parts to be made outside of required tolerances.
The Current State of Things

Aftermarket sensor installations can be difficult to standardize, difficult to install, and are subject to degradation


Where do you place the sensor, and what happens when it gets bumped out of place? Can your customer install and tune the sensor themselves?


Imagine you’re trying to learn a new tune on the piano, but the sheet music only has one note out of every ten.


Installation time and costs of sensors add up dramatically.

High Frequency Data

In 2020, our data science team launched a program focused on the application of high-frequency machine data for predictive maintenance with the goal of accelerating predictive analytics use cases for machine tools. Our team discovered a way to collect data at 1 kHz directly from the control of CNC machines without using sensors that can immediately be used as inputs to time-series or machine learning models to predict machine failures.

The Discovery
The Solution


Supercharge your predictive analytics applications with high-frequency machine data to diagnose, predict, and avoid failures on your manufacturing equipment. No sensors required.

mm20_icon_R2_po improve scheduling
Leverage high-frequency data directly from the machine control or from sensor data. Use this data as inputs to time-series or machine learning models.
mm20_icon_R2_predictive deploy solutions@4x
Deploy and manage custom algorithms to MachineMetrics Edge devices that process and analyze at the source to detect potential failures.
mm20_icon_R2_po workflow
When an algorithm is triggered, deliver operator actions via alerts/notifications to factory workers or automate a feed-hold that stops machines prior to equipment failure.
Use Cases
Use Case #1 Machine Diagnostics

Understanding why issues have occured on machines in the past has been a notoriously difficult task. While low-frequency data can accomplish condition-based monitoring, Trying to do condition-based monitoring on say, spindle load, requires higher fidelity.

Collecting high frequency data from the control delivers unprecedented visibility and fidelity into the health and condition of the machine, enabling diagnoses that were once impossible.

Use Case #2 Tooling Optimization

Pushing cutting tools too hard leads to high tooling costs and frequent downtime for changeovers. Not pushing machines may reduce tooling costs at the expense of throughput.

An increase in tool wear due to differences in material, environment, and cutting can be detected, allowing you to run your tools to full life every time.

Use Case #3 Quality Optimization

When tools are compromised, they don’t do their job right. This causes problems like bad finishes and incomplete cuts on parts that must then be scrapped once they make it to QA.

Reduce these issues with tool chatter detection. Predict when parts go out of spec before they need to be scrapped or when parts will soon become out of spec.

Use Case #4 Predictive Maintanance

Expensive tools that snap when they become over-stressed, breaking not only that tool but even those further down the line.

Detect when initial stress fractures are occurring in tools, and alert the operator to take them out of commission before it gets worse.

How do we know this is a game-changer?
A Case Study BC Machining

Leveraging high-frequency data on spindle load to determine when the tools will fail, BC Machining can now detect a tool failure with 99% confidence up to 40 minutes before it fails.

We are actuating the machine to perform a Feed-Hold when this algorithm is triggered to stop the breakage from happening.

Ready to empower your shop floor?
Get started with manufacturing analytics today.