In the field of Prognostics and Health Management (PHM), deep learning methods have shown excellent remaining useful life (RUL) prediction ability because of their powerful data fitting ability. Such methods require a large amount of failure history to train, but for industrial assets, their life-cycle data are often insufficient, and effective repairs or replacements are frequently carried out before the failure occurs. On the one hand, these suspension history data cannot be directly used by traditional deep learning methods, resulting in the certain loss of degradation information. On the other hand, the internal structure of industrial assets and the types of features are complex and diverse. Traditional methods use Euclidean space to represent relevant data, ignoring the correlation between features. Therefore, we develop a semi-supervised adversarial graph prediction (SAGP) framework that combines adversarial learning, graph neural networks, and semi-supervised training, using both failure and suspension histories for RUL prediction. Based on graph neural networks, SAGP can effectively obtain the degradation information in the failure and suspension history by representing the degradation data in the form of graphs and setting multi-objective functions. Through semi-supervised learning, SAGP looks for failure and suspension histories similar to the current state and generates simulated data through adversarial training to improve the robustness of the model and finally achieve RUL prediction. Tool, engine, and bearing datasets are used to verify the accuracy and reliability of the SAGP model.

Distributed navigation interference is a critical technique for degrading the performance of multi-element adaptive nulling antennas, where optimal spatial deployment of interference sources is pivotal to maximizing overall interference effectiveness. However, interference signal propagation is constrained by transmit power, path loss, and terrain occlusion, rendering optimal cooperative source deployment in complex terrain a core challenge in navigation spectrum analysis and interference management. To address this gap, this paper proposes DDL-NSGA-II, an improved NSGA-II algorithm for distributed navigation interference source deployment. By integrating the free-space propagation model with reference-plane-based viewshed analysis, the effective coverage of interference signals in 3D terrain is estimated, and a bi-objective model is constructed with multi-weight coverage rate and effective dispersion as optimization objectives. Three well-established mechanisms are adapted and integrated into standard NSGA-II for this specific problem: differential evolution mutation with binomial crossover, stage-wise dynamic deduplication, and external archive-assisted local search refinement. The contribution lies in their problem-specific integration and adaptation to integer-encoded multi-source deployment, which significantly enhances global exploration and convergence accuracy. Simulation results show that DDL-NSGA-II delivers high-coverage deployment schemes with favorable dispersion under varying terrain resolutions, source quantities, and single-station interference ranges. It outperforms three baseline algorithms in convergence, Pareto front coverage, and solution uniformity, providing robust algorithmic support for intelligent multi-source cooperative deployment in complex terrain.