Sensor Fusion – Combine machine vision AI with sensors to detect defects and drive action with ADLINK Edge™

Reading Time: 3 minutes

Head of Engineering and Architecture for ADLINK Technology

Issues on a conveyor-belt driven production line in a manufacturing facility can easily be missed or overlooked which can lead to damaged products and costly repairs. The issues can fall into two categories, problems with the:

The resulting downtime can be costly and lead to missed production targets. Manual quality-inspections can help prevent some problems, but is time consuming, inaccurate, and causes bottle-necks in performance.

The solution to these issues lies within ADLINK EdgeTM technology. ADLINK’s hardware and software not only monitors production line data, for example; vibration, temperature, load, etc., to identify system health issues as they are happening in real-time, ADLINK’s Machine Vision platform also has the capabilities to detect defects in products as they move along the conveyor line even at high speeds.

If an issue is identified, ADLINK EdgeTM drives actions to create notifications either visually or through electronic mechanisms, it can also control the speed of your conveyor systems and even stop them.

You can collect and store telemetry information generated at the edge locally in your system, or alternatively relay the data to cloud-based services leveraging ADLINK Edge cloud connectors. The result is a secure system that enables rich and informative decision-making to enable AI guided solutions such as quality-inspection of products in real-time, and alerts when actions are required.

Challenges: Detecting defects early to avoid production delays

Production lines produce a huge number of products every day, common issues that can occur are:

Solution: AI based defect detection drives actions

Automating defect detection requires an integrated, end-to-end system of hardware and software capable of generating insights in real time.

The solution is ADLINK’s IoT and machine vision platform also known as ADLINK EdgeTM.

Sensors capture physical data about the conveyor (temperature, load, speed, vibration, etc.) and use an ADLINK engine to produce a risk score for each conveyor to then take action. ADLINK EdgeTM software supports the seamless integration of software and hardware to capture, stream, process, understand, and act on all captured data whether it’s sensor data or vision.

If an issue is identified through machine vision AI or a high risk score on the conveyor system, ADLINK EdgeTM produces an alert and reduces the speed of the conveyor, this helps you to quickly identify defects and react to them appropriately.

How it works

The following video shows you the solution in action:

  1. An ADLINK NEON Smart Camera is fixed above the conveyor belt to capture images of the products moving along. The images are directly inserted into the ADLINK DeepStream pipeline application where a model performs real-time quality inspection on the products.
  2. The ADLINK MCM-100 is connected to sensors that are connected to the conveyor which monitor temperature, vibration, load, speed etc. The ADLINK OT Connect application gathers data from the sensors via Modbus and a vibration data acquisition node. It can also connect to OPC UA, Ethernet/IP and many more.
  3. The data from ADLINK’s hardware and software is published to the Data River and can be used by other applications running within the local network.
  4. The NodeRED application is configured to generate a risk score for the conveyor based from the sensor data in real time. This risk score is then published to the Data River to be used by other applications.
  5. ADLINK’s OT Connector applications cover a multitude of protocols (Modbus, OPC-UA, EthernetIP) in the conveyor example this connects to an OPC-UA server which enables the control of the motors speed within the conveyor so that when the risk score increases the motor slows or comes to a complete stop depending on how it is configured.

The following video shows the risk score increase due to a temperature increase which causes the conveyor to slow and then completely stop:

The real-time data gives you the information you need to make decisions about your machines and helps you to predict future maintenance.

ADLINK EdgeTM make production lines intelligent, we quickly and easily connect and integrate sensors, cameras, conveyors, automation systems, factory management systems and cloud to enable real-time communication between conveyor, employees and back-end systems. Using AI at the edge enables ultra fast intelligence and automation by deploying data closest to its source to decrease latency and enable real-time decision making and actions.