Automated blowhole detection
in production

During the processing of metals, alloys, concrete and plastics, especially during casting and the subsequent solidification of the parts, material shrinkage often results in cavities, known as blowholes. If blowholes, e.g. in aluminum, are not detected, weak points can occur in components that lead to defects in the finished product. In the automotive sector, for example, these can cause quality losses or safety defects and therefore high costs or worse.

Regardless of the industry and material, the formation of blowholes as a defect in production is responsible for committee. As a result, the total loss of the machining costs used for the casting (minus the pure material value) or cost-intensive reworking can lead to significantly higher production costs. A comprehensive inspection of shrinkage-sensitive parts is therefore essential. To this day, some outdated methods are still used. For example, the finished parts of the surface inspection are carried out with the naked eye or tapped with a hammer. Even if the experienced employee can recognize in this way whether a blowhole is present, external blowholes are not always immediately visible to the naked eye. Density determination using Archimedes' principle can also provide information about shrinkage in individual workpieces. A manual inspection of a workpiece in series casting is carried out either randomly or after a certain number of pieces. While parts were subjected to destructive testing in the past, non-destructive material testing is becoming increasingly common in various methods. These forms of cavity detection are still carried out by the employee.

However, the detection of blowholes by humans entails high personnel costs and is therefore only partially efficient. The human condition also leads to a lack of consistency in material testing, which results in fluctuations in error detection and consequently in the quality of the end product. Another problem is that inspection systems controlled by employees often reveal gaps in the documentation and therefore in the traceability of the inspected products. However, inadequately documented sorting of defective parts makes it impossible to trace the formation of blowholes and the causes cannot be eliminated.

Automatic blowhole detection therefore brings significant efficiency gains and leads to a significant increase in quality in production.

In order to avoid fluctuations in the quality of the end product, every metal component produced must be analyzed in the production chain. Critical blowholes must be detected extremely reliably and quickly. It is also essential to identify and document these blowholes. This documentation can then serve as the basis for measures to feed existing blowholes and prevent the formation of new blowholes. In order for a fully automated solution for blowhole detection to improve the existing production process, it should also be possible to implement the application in the existing system. elunic develops modern software solutions for Industry 4.0 that integrate blowhole detection as an automated step in production in a cost-efficient and fluctuation-free manner. The aim is to avoid the time-consuming training of employees and reduce downtime and the number of rejects. Efficient processes enable a better quality of the end product as well as a higher robustness of all components.

With the automated quality control AI.SEE™, elunic offers an application specially programmed for the respective production, which can analyze each part in production independently of the material and fully automatically and check it for blowholes. The special feeding with clear training data, which the application uses to learn the various reject criteria, creates an adaptive learning model that is constantly evolving and can therefore reliably detect even very small blowholes. In addition to size, blowholes also differ in shape and/or texture. AI.SEE™ therefore has the ability to understand the general concept of a blowhole and thus recognize all types of blowholes. The extensive data collection and analysis in AI.SEE™ enables the comprehensive tracing and revision of cavity-prone areas. In addition to measures to optimize future components, the implementation of real-time monitoring by the cloud-based system can offer further quality control options to reduce reject rates and increase production efficiency.

Are you interested? Then find out now about the extensive possibilities for reliable blowhole detection and prevention with AI.SEE™!