Create An Industry Anomaly Detection Solution

Run multiple independent anomaly detection workloads on a single system that runs multiple virtual machines through a Kernel-based Virtual Machine (KVM) host.

Target Operating System Ubuntu* 16.04 LTS
Time to Complete 45 minutes

GitHub* (C++)

What You Will Learn

Factories use existing programmable logic controllers to control equipment and may use several different devices or workloads for the human machine interface (HMI), data ingestion, and computer vision application. This reference implementation demonstrates how all these workloads can run independently on one system.

Gain insight into the following solutions:

  • Computer vision applications for IoT
  • Inference to analyze datasets
  • Industrial IoT market

Use the skills learned in this reference implementation to develop similar IoT solutions.

Learn to build and run an industry anomaly detection system with these capabilities:

Run numerous workloads independently on a single system.
Use a KVM on a host system to run multiple virtual machines (VMs)
Run the Object Flaw and Motor Defect Detector reference implementations and gather data for analysis

Workload Consolidation in Industrial IoT

How It Works

In this application, three VMs run on a host machine using a KVM as the hypervisor.

  • The first virtual machine (named OFD) runs the object flaw detector application. This application detects anomalies on objects moving on a conveyor belt, and then stores this data locally on an instance of InfluxDB*.
  • The second machine (named MDD) hosts the motor defect detector application, which also stores the data locally on InfluxDB.
  • Data visualization occurs on the third VM (named HMI) using Grafana* and data from the OFD and MDD InfluxDB.

flow chart graphic of how the industrial anomaly detection reference implementation worksflow chart graphic of how the industrial anomaly detection reference implementation works