Hybrid analysis of multiaxis electromagnetic data for discrimination of munitions and explosives of concern

Abstract

SUMMARY The remediation of land containing munitions and explosives of concern, otherwise known as unexploded ordnance, is an ongoing problem facing the U.S. Department of Defense and similar agencies worldwide that have used or are transferring training ranges or munitions disposal areas to civilian control. The expense associated with cleanup of land previously used for military training and war provides impetus for research towards enhanced discrimination of buried unexploded ordnance. Towards reducing that expense, a multiaxis electromagnetic induction data collection and software system, called ALLTEM, was designed and tested with support from the U.S. Department of Defense Environmental Security Technology Certification Program. ALLTEM is an on‐time time‐domain system that uses a continuous triangle‐wave excitation to measure the target‐step response rather than traditional impulse response. The system cycles through three orthogonal transmitting loops and records a total of 19 different transmitting and receiving loop combinations with a nominal spatial data sampling interval of 20 cm. Recorded data are pre‐processed and then used in a hybrid discrimination scheme involving both data‐driven and numerical classification techniques. The data‐driven classification scheme is accomplished in three steps. First, field observations are used to train a type of unsupervised artificial neural network, a self‐organizing map (SOM). Second, the SOM is used to simultaneously estimate target parameters (depth, azimuth, inclination, item type and weight) by iterative minimization of the topographic error vectors. Third, the target classification is accomplished by evaluating histograms of the estimated parameters. The numerical classification scheme is also accomplished in three steps. First, the Biot–Savart law is used to model the primary magnetic fields from the transmitter coils and the secondary magnetic fields generated by currents induced in the target materials in the ground. Second, the target response is modelled by three orthogonal dipoles from prolate, oblate and triaxial ellipsoids with one long axis and two shorter axes. Each target consists of all three dipoles. Third, unknown target parameters are determined by comparing modelled to measured target responses. By comparing the rms error among the self‐organizing map and numerical classification results, we achieved greater than 95 per cent detection and correct classification of the munitions and explosives of concern at the direct fire and indirect fire test areas at the UXO Standardized Test Site at the Aberdeen Proving Ground, Maryland in 2010.

A novel test ground for the equipment qualification of magnetic gradient sensors used for unexploded bomb detection

“…The statement that the depth of the object is several times the object's dimensions may be applicable for the case of smaller buried unexploded ordnance, like artillery projectiles (see e.g. the paper of Friedel et al, 2012), but has to be tested explicitly, as has been done here -in the case of UXBs, with dimensions of the ferrous objects in the range of one meter and an (worst case) inclination of 90°. It should be noticed, that a comparison of both calculation methods (of Sections 4.1 and 4.2) offers the opportunity to test the far field behavior based on simulated numerical data.…”

“…the paper of McFee et al (1990). Electromagnetic induction methods are methods of choice for the detection of buried ordnance, lying in lower depth (see for instance Friedel et al, 2012). Combinations of several methods -like electromagnetic induction methods and arrays of total-field magnetometers -are also discussed in the literature (Nelson and McDonald, 2001).…”

“…Billings, 2004;Butler, 2003;Friedel et al, 2012;McFee et al, 1990McFee et al, , 1994Munschy et al, 2007;Pawlowski et al, 1995;Zhang et al, 2007) that describe how to use buried unexploded ordnance (UXO) below a test ground in order to check locating and identifying algorithms with experimental data. In contrast, in this paper we describe how we used precisely calibrated coils positioned below a test ground -instead of buried ferromagnetic objects, which have the disadvantage of an unchangeable position and an unchangeable magnetic moment -to simulate the stray magnetic fields of unexploded bombs in order to test the capabilities of sensor systems and to train and to rate the skills of bomb detection teams.…”

Machine learning classification of permeable conducting spheres in air and seawater using electromagnetic pulses

“…EMI methods typically utilize a Heaviside step-off pulse. However, other pulse types have been investigated along with machine learning classification, such as the use of a triangle waveform in [89]. Field observations were used to train a self-organizing map (a type of unsupervised artificial neural network), and target parameters including depth, In other work, non-probabilistic (support vector machines, random forests, decision trees) and probabilistic (gradient boost, multi-layer perceptron, logistic regression) machine learning algorithms were trained to classify metal objects using a dictionary of MPT spectral signatures in the frequency domain [90].…”