In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can solve the problem of the unlabeled testing dataset in transfer learning. Moreover, Convolutional Neural Network (CNN) is the most widely used network among existing domain adaptation approaches due to its powerful feature extraction capability. However, network designing is too empirical, and there is no network designing principle from the frequency domain. In this paper, we propose a unified convolutional neural network architecture from a frequency domain perspective for a domain adaptation named Frequency-domain Fusing Convolutional Neural Network (FFCNN). The method of FFCNN contains two parts, frequency-domain fusing layer and feature extractor. The frequency-domain fusing layer uses convolution operations to filter signals at different frequency bands and combines them into new input signals. These signals are input to the feature extractor to extract features and make domain adaptation. We apply FFCNN for three domain adaptation methods, and the diagnosis accuracy is improved compared to the typical CNN.

Asteroid impacts pose a major threat to all life on Earth. The age of the dinosaurs was abruptly ended by a 10-km-diameter asteroid. Currently, a nuclear device is the only means of deflecting large Potentially Hazardous Asteroids (PHAs) away from an Earth-impacting trajectory. The Enhanced Kinetic Impactor (EKI) concept is proposed to deflect large PHAs via maneuvering space rocks. First, an unmanned spacecraft is launched to rendezvous with an intermediate Near-Earth Asteroid (NEA). Then, more than one hundred tons of rocks are collected from the NEA as the EKI. The NEA can also be captured as the EKI if the NEA is very small. Finally, the EKI is maneuvered to impact the PHA at a high speed, resulting in a significant deflection of the PHA. For example, to deflect Apophis, as much as 200 t of rocks could be collected from a NEA as the EKI based on existing engineering capabilities. The EKI can produce a velocity increment (∆v) of 39.81 mm/s in Apophis, thereby increasing the minimum geocentric distance during the close encounter in 2029 by 1,866.93 km. This mission can be completed in 3.96 years with a propellant cost of 2.98 t. Compared with a classic kinetic impactor, the deflection distance can be increased one order of magnitude. The EKI concept breaks through the limitation of the ground-based launch capability, which can significantly increase the mass of the impactor. We anticipate that our research will be a starting point for efficient planetary defense against large PHAs.

Context. The near-Earth object (NEO) 2022 EB5 is the fifth NEO found prior to entering the Earth's atmosphere. It fragmented over the Norway Sea on 2022 March 11 about two hours after being discovered by the astronomer Krisztián Sárneczky at Konkoly Observatory in Hungary. The Center for Near-Earth Object Studies (CNEOS) at NASA detected the visible radiation emitted at the time of its atmospheric entry. The Jet Propulsion Laboratory (JPL) and European Space Agency (ESA) derived its orbital elements based on observations of its pre-atmospheric orbit. Aims. This paper aims to calculate the physical properties of this NEO, in particular, the bulk strength, type of the material, albedo, size, and mass, based on observations of its peak brightness at the time of its atmospheric entry. In addition, the heliocentric elements are computed from its interaction with Earth's atmosphere and compared with those derived from observations by JPL and ESA, respectively, to evaluate the accuracy of our method. Methods. The flight equations of 2022 EB5 were inversely integrated from the peak brightness to the atmospheric boundary via the fourth-order Runge-Kutta method. A pancake model was utilized to simulate the fragmentation of the impactor. Parameters needed to complete the integration process that were unknown were set to be optimization variables and determined via a genetic algorithm. Results. The results obtained show that 2022 EB5 was most likely a C-type asteroid with a maximal bulk strength of 2 MPa, diameter of 5–6 m, cometary density, and very low albedo that is no greater than 0.025. In addition, considering the effects of the atmosphere is helpful in getting a more accurate measurement for the semi-major axis, eccentricity, and inclination, although the accuracy of orbital elements strongly depends on the accuracy of USG sensors.