MiDAS

Use Cases

The Challenge

There are several factors to consider when performing condition-based maintenance on the Phase 3 induction motor, including shaft vibrations and winding temperature. However, the challenge for this particular use case is related to power.

Often, a misaligned shaft can cause noise and vibrations, which can be transmitted to the motor from the machine or power transmission system. They can also be caused by electrical unbalance in the motor.

Electrical unbalance occurs when the magnetic attraction between the stator and rotor is uneven around the periphery of the motor. This causes the shaft to deflect as it rotates, creating a mechanical unbalance. An uneven air gap, usually from badly worn bearings, can also produce an electrical unbalance.

Electrical unbalance usually escalates into an electrical failure such as an open stator or rotor winding. Modular Industrial Detect and Sense - MiDAS - An IIoT 4.0 solution for Power Analytics can help to prevent this.

The Solution

MiDAS can help to prevent electrical unbalance or voltage imbalance in phase 3 induction motors by allowing condition-based monitoring and Power management.

MiDAS ensures power savings by providing actionable information based on the data collected by the sensors by monitoring machine power parameters, as well as using AI and Ml to alert you to power consumption issues, lowering your energy bills, and improving your equipment life and plant maintenance practices.

For this particular use case, MiDAS can help through the following benefits:

Power measurement—benchmarking for plants and assets
Reporting on high consuming assets
Condition-based monitoring to achieve better utilization
Data collection for future benchmarking and improvements

MiDAS allows the application of analytics using AI and ML techniques. It allows measurement of Harmonics up to 32nd Level at 8 kHz sampling rate as well as monitoring of Fast Fourier Transform (FFT) from measured Harmonics.

When you monitor FFT (Fast Fourier Transform), you see all the frequencies and their amplitude but you lose the sense of time. It will why MiDAS also allows STFT (Short Time Fourier Transform) based analytics from the measured data.

STFT data is converted into an image and sent to the cloud for further analysis. AI-based trained engine compares the image and relates it with cause. A Convolutional Neural Network engine is used for the prescriptive analysis. New fault conditions are analyzed by domain experts to describe the event. These new fault conditions are added to our analysis.

The Result

The result is a confusion matrix for the motor and pump. In this confusion matrix, all other measurements such as Vibration, Acoustic apart from Power, are also considered.

On the analysis graph, the X-Axis shows the Predictions stored in the trained engine and the Y-axis shows the number of actual different types of faults. For example, the supply fan has 4 different types of faults. It has been found that our engine detects these faults using our ML-based image analytics with 100% accuracy.

GET STARTED WITH MiDAS

This website uses cookies

We use cookies to personalise content and ads, to provide social media features and to analyse our traffic. We also share information about your use of our site with our social media, advertising and analytics partners who may combine it with other information that you've provided to them or that they've collected from your use of their services. You consent to our cookies if you continue to use this website.

Use Case - Voltage Imbalance in Induction Motors

The Challenge

The Solution

The Result

This website uses cookies