Micro milling is widely used to manufacture micro parts due to its obvious advantages. The minimum undeformed chip thickness, the effective rake angle, and size effect are the typical characteristics and closely related to each other in micro milling. In this paper, the averaging method is proposed to quantitatively estimate the effective rake angle in the cutting process. The minimum undeformed chip thickness is explained based on the effective rake angle and determined to be 0.17 rn (tool cutting edge radius). Then, micro milling experiment was conducted to study the effect of the minimum undeformed chip thickness. It is found that the minimum undeformed chip thickness results in the unstable cutting process, the uneven peaks on cutting force signal, and the dense characteristic frequency distribution on frequency domain signal. The dominant ploughing effect induces the great specific cutting energy and the deteriorated surface roughness due to the minimum undeformed chip thickness.
Recent studies have proven that synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNN) are vulnerable to adversarial examples. However, existing attacks easily fail in the case where adversarial perturbations cannot be fully fed to victim models. We call this situation perturbation offset. Moreover, since background clutter takes up most of the area in SAR images and has low relevance to recognition results, fooling models with global perturbations is quite inefficient. This paper proposes a semi-white-box attack network called Universal Local Adversarial Network (ULAN) to generate universal adversarial perturbations (UAP) for the target regions of SAR images. In the proposed method, we calculate the model’s attention heatmaps through layer-wise relevance propagation (LRP), which is used to locate the target regions of SAR images that have high relevance to recognition results. In particular, we utilize a generator based on U-Net to learn the mapping from noise to UAPs and craft adversarial examples by adding the generated local perturbations to target regions. Experiments indicate that the proposed method effectively prevents perturbation offset and achieves comparable attack performance to conventional global UAPs by perturbing only a quarter or less of SAR image areas.
Convolutional neural networks (CNN) have been widely used in the field
of synthetic aperture radar (SAR) image classification for their high
classification accuracy. However, because CNNs learn a fairly
discontinuous input-output mapping, they are vulnerable to adversarial
examples. Unlike most existing attack manners that fool CNN models with
complex global perturbations, this study provides an idea for generating
more dexterous adversarial perturbations. It demonstrates that minor
local perturbations are also effective for attacking. We propose a new
attack method called local aggregative attack (LAA), which is a
black-box method based on probability label information, to reduce the
range and amplitude of adversarial perturbations. Our attack introduces
the differential evolution (DE) algorithm to search for the optimal
perturbations and applies the maximum between-class variance method
(OTSU algorithm) to accomplish pixel-level labelling of the target and
background areas, enabling attackers to generate adversarial examples of
SAR images (AESIs) by adding small-scale perturbations to specific
areas. Meanwhile, the structural dissimilarity (DSSIM) metric optimises
the cost function to limit image distortion and improve attack
stealthiness. Experiments show that our method achieves a high attack
success rate against these CNN-based classifiers, and the generated
AESIs are equipped with non-negligible transferability between different
models.
Abstract. Current Statistical (CS) model is a good adaptive filtering model for maneuvering target tracking. While, the performance of CS model depends on the maneuvering frequency, and becomes poor when tracking weak maneuvering targets. Firstly, the innovation of the filtering is used to reduce the dependence on the constant of maneuvering frequency. Secondly, in order to improve the performance for weak maneuvering targets, Constant Velocity (CV) model is used to compete with CS model in the framework of Interacting Multiple Model (IMM) algorithm. Thirdly, to avoid the over-competition and enhance the probability of superior model, a time-varying model transition probability function is proposed with the current measure. Simulation results show that this method greatly improves the performance for weak maneuvering targets, and the performance for strong maneuvering targets is similar to that of the CS model.
The performance of a single neural network can vary unexpectedly corresponding to different classification tasks, and thus the network with fixed structure may lack flexibility and often lead to overfitting or underfitting. It is urgent, also the main objective of this paper, to deal with the limitation of the fixed neural network structure on classifying radar signals in different electromagnetic environments. We in this paper propose a variable network architecture search (NAS) mechanism, called balanced-NAS framework, and apply it in specific emitter identification (SEI) to greatly improve the flexibility of model searching. In the proposed balanced-NAS framework, a "blockcell" structure and a controller based recurrent neural network (RNN) are utilized to design models automatically according to external environment. In particular, a balance function is also proposed and utilized in the balanced-NAS framework, acting on the RNN controller to take both the validation accuracy and computational budget into consideration while searching for ideal models. The efficiency of the searching process is further enhanced by exploiting a progressive strategy to design simple and complicate child models where unpromising ones after each evaluation process are obsoleted to release searching space. Simulations and experiments indicate that the proposed balanced-NAS framework is extremely efficient and outperforms the conventional algorithms in classifying radar signals in different environments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.