Predictive Maintenance

Many companies offer predictive maintenance solutions, but unlike other companies, our approach is faster, more cost effective and requires fewer resources. We can achieve this using a variety of “templates” that follow a six-step process. These steps include:

 

Data collection. We collect data from multiple sources, including third-party sources, for any given time period. The result is an intentional and effective data acquisition approach, which only yields the necessary information for analysis and producing real-time, impactful results.

 

Signal processing. We remove outliers and “noise” to get clean data.

 

Feature extraction. We then convert the raw, clean data into meaningful features that we use to “train” our AI algorithms.

 

Health assessment. Our AI machine learning model creates a fingerprint of a healthy and unhealthy machine. Our model compares machine performance to these fingerprints to assess machine health over time.

 

Trending/prediction. Our models compare machine health over time to identify trends and calculate remaining useful life to determine when the machine will likely fail, down to the day, number of cycles and number of shifts.

Fault diagnosis. Once our models determine a failure is likely to happen, we can determine the root cause of the failure so maintenance teams can respond quickly before the machine experiences downtime.

Industrial Robots

Our industrial robot templates observe each axis on an industrial robot to monitor servo-motor torque and provide fleet-based health assessments and predict failure. Unlike other offerings, our industrial robot predictive maintenance solution:

 

  • Does not require any equipment sensors to be installed on the robot
  • Can monitor any robot regardless or manufacturer, age or controller
  • Is quick to deploy and can be operating in a few weeks
  • Reduces maintenance time and costs because technicians know the exact component that requires attention
  • Reduces spare part inventories

 

Download our Industrial Robots Technology brochure. IoTco-FS_Robot-Brochure_2018

Machine Tools

Our smart machine templates analyze all the critical components of a CNC machine to assess its health and predict failure. These templates work on any CNC machine and any controller. They are also quick to deploy, so you can begin analyzing data after running them for only a few weeks. Templates include:

 

  • Tool condition monitoring. We look at the tool degradation as it cuts a part to assess misalignment, chatter and vibration, which could compromise part quality.

 

  • Spindle performance monitoring. Using vibration sensors, we can evaluate spindle performance and provide a health assessment within weeks, not months.

 

  • Feed axis (ball-screw) monitoring. We can analyze the health of the feed axis without the need for sensors.
  • Coolant analysis. We use an oil analysis sensor to monitor the pH and other qualities to determine when the coolant needs to be changed before it affects machine performance.

 

  • Alarm (fault) mining. We capture and analyze alarm faults to determine patterns, so we can predict when alarms will occur and determine the root cause of the alarm.

 

Download our brochure. IoTco-PDX_Brochure_2018

Stamping Presses

We monitor the health of stamping presses, including hydraulic, servo, electric and giant stamping presses, via two templates.

 

Vibration-based fault protection. We can mount sensors inside the machine to analyze the vibrations of the stamping press as well as the vibration of the die itself.

 

Acoustic-based analytics. When sensors can’t be installed inside the stamping press, we can mount an acoustic sensor near the machine to capture machine frequencies and measure press degradation.

Download our brochure. [LINK TO IoTco-PDX_Brochure_2018.pdf. URL TBD]

Ancillary Equipment

We monitor the health of ancillary equipment, including HVAC compressors and chillers, pumps and motors via the following templates:

 

Compressors and chillers.  We do not use sensors to capture equipment performance; instead, we analyze current and voltage data straight from the controller.

 

Pumps. We use sensors to monitor vibration, pressure and flow to assess pump health and predict failures.

 

Motors. We assess the motor’s current and vibration to assess the health and predict failures.

Download our brochure. [LINK TO IoTco-PDX_Brochure_2018.pdf. URL TBD]