Enhanced anomaly detection in wire ropes by combining structure and appearance

Abstract

Automatic visual surface inspection is a challenging task, which has become important for quality assurance in the last years. Wire rope inspection is a special problem within this field. Usually, the huge and heavy ropes cannot be detached. Thus, an inspection of the ropes must be conducted, while the ropes are in use. The rope surface exhibits various appearance characteristics so that the existing, purely appearance-based approaches tend to fail.We explicitly integrate information about the object geometry, which we obtain by aligning a sequence of 2d rope images with a perfectly regular 3d model of the rope. The rendering equation is used to link object geometry to the observed rope appearance. Based on the connection between geometry and surface appearance we build a probabilistic appearance model which serves as representation for normal surface variations. A robust localization of rope surface defects is achieved by means of anomaly detection. The presented approach has no need for knowledge about the illumination setting or the reflectance properties of the material.An evaluation on real-world data from ropeways leads to an accuracy comparable to that of a human expert. With an accuracy of 95% and a false-alarm-rate of 1.5% the approach outperforms all other existing approaches.

A Review of Non-Destructive Damage Detection Methods for Steel Wire Ropes

“…For the defects of WR, the histogram of oriented gradient feature was the best, followed by the local binary patterns feature. In the work of [48,49], Wacker et al established a probabilistic appearance model as a representation of normal surface changes combined with the structure and appearance of the WR and realized the detection of WR abnormal surface. For surface defects of thin metallic wires, an automatic optical detection technique was presented by Sanchez-Brea et al in [50].…”

Nondestructive Testing of Composite Materials

“…Self-magnetic flux leakage (SMFL) is assumed to take place in the stress concentration areas of ferromagnetic materials affected by mechanical load under the Earth's magnetic field [46], and this condition can remain even after removing the load, creating detectable magnetic leakage at the material surface [47]. Measuring SMFL at the surface of the materials helps in estimating their stress-strain states (SSSs), which is an important parameter in determining a structure's reliability [48]. Therefore, the relation between localized stress and oriented magnetic domains is useful for detecting defects in ferromagnetic materials within the background magnetic field of the Earth [49].…”

Condition Monitoring Technologies for Steel Wire Ropes – A Review

“… Surface contamination by e.g. oil, mud, organic growth and even water  The method is not applicable for internal wire breakings  Outdoor lighting conditions are challenging, but can be removed by boxing in the camera and use active light source  Obtaining sufficient number of supervised training data sets for all fault classes An interesting research on SWR was reported by Wacker and Denzler (2013), where anomaly detection is used for avoiding the need of appropriate training data sets. A three dimensional mathematical model of the rope structure is developed, which is projected onto a two dimensional figure.…”

“…Figure 6. General framework used for the detection of surface defects in wire ropes (Wacker &Denzler, 2013) Wacker andDenzler (2013) reported very precise estimation of strand lay length, especially when the result was corrected for deformations. During a real world experiment using four cameras to cover the complete rope surface, 95% defection detection accuracy was obtained, with 1.5% false alarm rate.…”