[2A3] Machine learning for plane wave imaging
T Koskinen¹, T Tyystjärvi¹,², O Jessen-Juhler¹ and I Virkkunen¹,²
¹Trueflaw Ltd, Finland
²Aalto University, Finland
Phased array ultrasonics has enabled the recording of an ever-increasing amount of data from inspection targets. With the latest advancements in the total focusing method (TFM) with plane wave imaging (PWI), the amount of data has increased exponentially when compared to conventional ultrasonic methods. As more data allows for more reliable evaluation, the cost of evaluation also increases. Since there is more data for the inspector to evaluate, the inspector’s job becomes more difficult and labour-intensive with the modern technology. Moreover, as phased array techniques evolve to even more sophisticated approaches such as the total focusing method and the latest form, the plane wave imaging total focusing method (PWI-TFM), reading raw ultrasonic data is too convoluted for human inspectors. While the idea is to show a pre-calculated image to the inspector, the data allows for multiple different ways of presenting the data to the inspector, even though these representations are not normally used. Machine learning (ML)-powered inspection enables the full use of all the data, while allowing the best possible presentation for the inspector.
In this paper, the authors demonstrate PWI-TFM inspection powered by a machine learning model. The ML model is used to scan the data and present the flaw indications to the inspector.
In this paper, the authors demonstrate PWI-TFM inspection powered by a machine learning model. The ML model is used to scan the data and present the flaw indications to the inspector.
