After wars, some unexploded bombs remained underground, and these faulty bombs seriously threaten the safety of people. The ability to accurately identify targets is crucial for subsequent mining work. A deep learning algorithm is used to recognize targets, which significantly improves recognition accuracy compared with the traditional recognition algorithm for measuring the magnetic moment of the target and the included geomagnetism angle. In this paper, a ResNet-18-based recognition system is presented for classifying metallic object types. First, a fluxgate magnetometer cube arrangement structure (FMCAS) magnetic field feature collector is constructed, utilizing an eight-fluxgate magnetometer sensor array structure that provides a 400 mm separation between each sensitive unit. Magnetic field data are acquired, along an east–west survey line on the northern side of the measured target using the FMCAS. Next, the location and type of targets are modified to create a database of magnetic target models, increasing the diversity of the training dataset. The experimental dataset is constructed by constructing the magnetic flux density tensor matrix. Finally, the enhanced ResNet-18 is used to train the data for the classification recognition recognizer. According to the test findings of 107 validation set groups, this method’s recognition accuracy is 84.1 percent. With a recognition accuracy rate of 96.3 percent, a recall rate of 96.4 percent, and a precision rate of 96.4 percent, the target with the largest magnetic moment has the best recognition impact. Experimental findings demonstrate that our enhanced RestNet-18 network can efficiently classify metallic items. This provides a new idea for underground metal target identification and classification.

In order to classification the kinds of metal objects, we propose a recognition method based on ResNet-18. First, we built a magnetic field feature collector that we called FMCAS (Fluxgate magnetometer cube arrangement structure), using 8 fluxgate magnetometer sensor array structures to ensure a distance of 400mm between each sensitive unit. We use FMCAS to collect the magnetic field data of a survey line along the east-west direction on the north side of the measured target. Next, we change the location and type of the target and build a database of magnetic target models, which enriches the diversity of the training dataset. Construct the magnetic flux density tensor matrix to create the experimental dataset. Finally, we use the improved ResNet-18 to train the data to get the recognition classification recognizer. The recognition accuracy of this approach is 84.1%, according to the test results from 107 groups of validation sets. The target with larger magnetic moment has the best recognition effect, with a recognition accuracy rate of 96.3%, a recall rate of 96.4%, and a precision rate of 96.4%. Experimental results show that our improved RestNet-18 network can effectively handle the classification of metal objects.