It creates a warm and inviting atmosphere. Its natural grain and color tones have a lively effect and add character to a room. We are talking about classic wood flooring—usually laminate, and optionally with a click system for easy installation.

Scheucher Holzindustrie GmbH, from Mettersdorf, Austria, is now in its fourth generation of manufacturing high-quality wood floors, combining tradition with modernity in its production. The company relies on image processing with artificial intelligence—more precisely, IDS NXT—to inspect the glue joints of its multilayer wood flooring with an all-in-one system for intelligent cameras.

Application

Not all wood floors are the same. In addition to solid variants, multilayer flooring is particularly popular. Several aspects factor into the manufacture of a high-quality, durable, and user-friendly product.

The choice of wood species, for example, influences the stability and appearance of the flooring. As the term multilayer suggests, this flooring consists of several layers—in particular, a core layer and a wear layer. Scheucher uses spruce or pine as backing. A variety of wood species can be chosen for the wear layer.

Structure of a three-layer finished flooring for floating installation or full-surface gluing with click system

A major advantage of “prefinished flooring” is its ease of installation. Many types can be laid as a floating floor that doesn’t need to be glued down. With a little manual skill, even inexperienced people can install their own wood floor. A click system ensures the exact fit of the planks, which are simply clicked directly into each other. This saves time and reduces the workload. It’s important that the click system is milled with high precision so each panel’s interlock is stable and precise. Incorrect milling can lead to instability and problems during installation.

The same applies to the adhesive bond between the core layer and the wear layer of the flooring. The adhesive must be applied evenly to ensure complete coverage and a uniform bond between layers. Air inclusions or irregular application quantities can lead to cavities, impairing the product’s durability.

“In the profiling for our MULTIflor floors, a special click profile is milled into the planks,” says Klaus Bauer, Research & Development at Scheucher. “During this process, two intelligent IDS NXT cameras are used to check the presence of adhesive in the adhesive joint between the core and the backing layer.”

Each panel’s fit must be stable and precise.

Intelligent quality control without a PC

Scheucher illuminates the already glued flooring planks with UV light. When the adhesive fluoresces, adhesive residues become visible. Scheucher relies on image processing with artificial intelligence to detect faulty floorboards.

Two IDS NXT rio cameras are used for each system. The intelligent models become powerful inference cameras by loading a neural network. They detect the fluorescent adhesive joints and process the image data directly “on the edge” via FPGA and pass the result on to the downstream process. The embedded solution makes the host PC redundant and reduces energy consumption and system costs. Thanks to screwable and IP-protected connectors as well as robust housing, they are also well suited to industrial use. A standardized OPC UA industrial protocol enables direct communication with machines and control systems.

IDS NXT rio camera detects faulty glue joints between flooring layers.

Image processing with AI without prior knowledge of deep learning

Application development and integration into the manufacturer’s existing production system was quick and easy with the help of the IDS NXT rio Experience Kit. A complete inference camera solution for AI applications in industrial image processing, it contains all the components that a user needs to create, train, and execute a neural network in a productive environment. The package includes the required hardware—in the form of an IDS NXT rio industrial camera with 1.6 MP Sony color sensor including power and data cable, tripod adapter, and lens—as well as the required software in the form of an “IDS lighthouse” license. This allows users to concentrate fully on the planned application without having to worry about deep learning, image processing, or camera programming.

“In our profiling system, we had not used any image processing, neither rule-based nor intelligent, for the quality control of our bonded joints until now,” says Bauer. “Nevertheless, it was our goal, even as laymen, to solve this requirement using AI. Because we are looking for errors that are extremely rare, our challenge was to find a sufficient number of ‘bad partial images’ to train the neural network. And we succeeded. In the end, we needed around 60 good and bad part samples before the AI had learned to recognize the threshold between OK and NOT OK.”

Faulty panels can be reliably sorted out and reworked. The system prevents planks with defects in the layer bonding from being delivered to customers. “This makes us one of the few manufacturers on the market to achieve a 100% inspection in this regard,” says Bauer. And it takes less than 90 milliseconds to check a floorboard.

OK and NOK panels: The bad part (lower) shows a presumably insufficient bonding in the right third.

Outlook

In this example, the inspection of the glued joint could also be solved using classic rule-based image processing, though with increased programming effort. However, it was important to Scheucher to find an intelligent solution.

This means that the company is prepared for further applications. As Bauer says, “The task was a good introduction to AI-supported image processing for us, especially because the learning curve was quick.”

This paves the way for further applications and future-proof, efficient production. With the help of intelligent image processing systems, objects can be classified or checked for defects, deviations, and quality problems. This can reduce errors and increase productivity in a wide range of industries and applications.

The IDS AI-based, all-in-one vision system isn’t highly complex or reserved purely for experts. Scheucher and IDS NXT have something in common: Thanks to sophisticated systems, even nonprofessionals can use it and achieve first-class results for a high-quality product.

Published by IDS Imaging Development Systems GmbH.

The IDS NXT rio Experience Kit is the complete inference camera solution for AI applications in industrial image processing. Model used: IDS NXT rio. Camera family: IDS NXT.