Characterisation of clustered cracks using an ACFM sensor and application of an artificial neural network

Abstract

The alternating current field measurement (ACFM) technique can be applied for surface-breaking fatigue crack detection and sizing; the link between the ACFM signal and crack size is well understood for individual cracks. However, the ACFM response to multiple clustered cracks is significantly different to that of isolated cracks. In railway rails the high wheel-rail forces can lead to rolling contact fatigue (RCF) cracks. Often cracks appear together in small clusters or in long stretches. The accurate characterisation of such fatigue cracks is essential for carrying out efficient and safe repair and maintenance. This paper presents a method for sizing the important sub-surface section of multiple cracks using ACFM via the application of an artificial neural network (ANN). The approach is demonstrated using a railway case study: a simulation-based dataset of signal response covering the range of RCF cracks typically seen in in-service railway tracks has been generated to give a thorough representation of the effect of clustered crack parameters on the ACFM response. A 5×5×2×1 multi-layer ANN has been optimised and trained using the validated simulation database to learn the inverse relationship between the crack pocket length (desired output) and the ACFM signal for a given cluster of RCF cracks. The network has been evaluated on a set of experimental data to size cracks of known dimensions from ACFM measurements and also on unseen simulation data. Results from both simulation and experiment show that the approach presented can be used to size clustered cracks to approximately the same degree of accuracy as is possible for isolated cracks.

A Novel ACFM Probe With Flexible Sensor Array for Pipe Cracks Inspection

“…When the workpiece being inspected is a pipe, it is difficult for the probe to induce a uniform current of stable intensity on the surface of the pipe. The commercial ACFM micropencil probe that is manufactured by TSC is used to size the subsurface section of multiple cracks and determine the propagation angle for non-vertical surface-breaking cracks in rail and wheels [10], [20]- [23]. However, the detection range of the micropencil probe is relatively small and the efficiency is relatively low.…”

Prediction of RCF clustered cracks dimensions using an ACFM sensor and influence of crack length and vertical angle

“…A 3D finite element (FE) model was developed using the AC/DC module in COMSOL Multiphysics [17]. This model has been verified previously by experimental measurements for single cracks and uniformly sized crack clusters [4,14,16]. For the modelling work, RCF cracks are assumed to have a semi ellipse shape with elliptical ratios from 1 to 1.75, which has been shown to approximate real (light to moderate) RCF cracks in rails removed from service [3].…”

“…Sizing for crack clusters using an algorithm based on modelling and measurements for single cracks inevitably leads to errors, as shown in [4]. Responses of ACFM Bx signals to various surface lengths, inner spacings and crack numbers for crack clusters have been reported but only cracks with vertical angles of > 30° were considered [16]. Previous studies [14,22] have shown that shallow vertical angles (< 30°) give different Bx signals compared to those obtained for cracks with vertical angles >30° for single and clustered cracks, leading to under estimation of crack pocket lengths.…”

Identification of Tiny Surface Cracks in a Rugged Weld by Signal Gradient Algorithm Using the ACFM Technique

“…Leng et al proposed the combined metal magnetic memory (MMM) and the ACFM technique for the detection and evaluation of critical weld joints in a jack-up offshore platform [20]. Rowshandel et al presented the artificial neural network (ANN) for sizing the important subsurface section of the multiple cracks using ACFM [21]. These methods obtained good characteristic signals from the cracks without lift-off variations [22,23].…”