Präsentation
Filtern
Dokumenttyp
- Vortrag (4)
Sprache
- Englisch (4)
Referierte Publikation
- nein (4)
Schlagworte
- Eddy current (4) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (4)
In recent years, additive manufacturing technologies have gained in importance. Laser powder bed fusion can be used for complex functional components or the production of workpieces in small quantities. High safety requirements, e.g. in aerospace, demand comprehensive quality control. Therefore, non-destructive offline inspection methods such as computed tomography are used after production. Recently, online non-destructive testing methods such as optical tomography have been developed to improve profitability and practicality. In this presentation, the applicability of eddy current inspection using GMR sensors for online inspection of PBF-LB/M parts is demonstrated. Eddy current testing is performed for each layer during the production process at frequencies uo to 1.2 MHz. Despite the use of high-resolution arrays with 128 elements, the testing time is kept low by an adapted hardware. Thus, the measurement can be performed during the manufacturing process without significantly slowing down the production process. In addition to the approach, the results of an online eddy current test of a step-shaped test specimen made of Haynes282 are presented.
The rails of modern railways face an enormous wear and tear from ever increasing train speeds and loads. This necessitates diligent non-destructive testing for defects of the entire railway system.
Non-destructive testing of rail tracks is carried out by rail inspection trains equipped with ultrasonic and eddy current test devices. However, the evaluation of the gathered data is mainly done manually with a strong focus on ultrasonic data, and defects are checked on-site using hand-held testing equipment. Maintenance measures are derived based on these on-site findings.
The aim of the AIFRI project (Artificial Intelligence For Rail Inspection) is to
- increase the degree of automation of the inspection process, from the evaluation of the data to the planning of maintenance measures,
- increase the accuracy of defect detection,
- automatically classify detected indications into risk classes.
These aims will be achieved by training a neural network for defect detection and classification. Since the current testing data is unbalanced, insufficiently labeled and largely unverified we will supplement fused, simulated eddy current and ultrasonic testing data in form of a configurable digital twin.
Non-destructive testing of rail tracks is carried out by using rail inspection cars equipped with ultrasonic and eddy current measurement. The evaluation of test data is mainly done manually, supported by a software tool which pre-selects relevant indications shown to the evaluators. The resulting indications have to be checked on-site using hand-held testing equipment. Maintenance interventions are then derived on the basis of these on-site findings.
Overall aim of the AIFRI (Artificial Intelligence For Rail Inspection) project - funded by the German Federal Ministry of Digital and Transport (BMDV) as part of the mFUND programme under funding code 19FS2014 – is to increase the degree of automation of the inspection process from the evaluation of the data to the planning of maintenance interventions. The accuracy of defect detection shall be increased by applying AI methods in order to enable an automated classification of detected indications into risk classes. For this purpose, data from both eddy current inspections and ultrasonic inspections will be used in combination.
Within the framework of this data-driven project, relevant defect patterns and artefacts present in the rail are analysed and implemented into a configurable digital twin. With the help of this digital twin virtual defects can be generated and used to train AI algorithms for detection and classification. With the help of reliability assessment trained AI algorithms will be evaluated with regard to the resulting quality in defect detection and characterisation.
A particular aspect of the development of AI methods is the data fusion of different NDT data sources: Thereby, synergies are used that arise from linking eddy current and ultrasonic inspection data in a combined model.
In the course of the project a demonstrator consisting of the developed IT-tool and an asset management system will be implemented and tested in the field using real-world data.
Main concept of magnetism and, therefore, of magnetic imaging can be subdivided into different levels, macroscopic, magnetic domain, and atomic. While conventional sensor solutions cover only the macroscopic level, the spatial resolution of GMR (Giant Magneto Resistance) sensors go down to the domain scale. In addition, those low cost sensors are well suited for automotive and industrial applications, particularly high-speed solutions. Main reason is their outstanding performance in terms of high spatial resolution, high accuracy, high bandwidth combined with field sensitivity, energy efficiency and durability.
In contrast to industrial use, down to the present day GMR sensors do not get beyond scientific scope in case of non-destructive testing (NDT) applications. Nevertheless, there are scientific and industrial NDT applications in which adapted GMR sensor can be promising compared to the conventional NDT methods.
This contribution summarizes findings at the BAM over the last decade which demonstrates the preeminent properties of GMR-based testing solutions. This comprises the active and passive testing of different materials with hidden defects and flaws near geometric boundaries like edges where conventional methods meet their limits. Another promising application for adapted GMR sensors is the characterization of magnetic materials, where the sensors provide additional information on microstructure, mechanical stress state, phase transformations and their interaction with magnetic fields. The examples show the need and benefit of NDT adapted GMR sensors.