Fast motion and low vibration are often conflicting requirements in industrial robots. Due to joint flexibility, operating at high accelerations can excite mechanical resonance, leading to vibrations that may accelerate gearbox wear and degrade control performance. Effectively suppressing these vibrations requires accurate modeling, identification, and compensation of joint flexibility across the entire workspace and under various payloads. The conventional two-mass model, which focuses on joint rotational stiffness in the gearbox, fails to capture the global flexibility characteristics, as flexibility also arises from bending in the bearings. This article presents a practical multi-local-mode-based model and the corresponding identification method to globally characterize a manipulator’s joint flexibility. Based on this model, a vibration suppression method is developed to mitigate mechanical resonance, achieving low vibration even at high acceleration. Comparative experiments demonstrate that the proposed approach effectively suppresses vibrations across the workspace and under various payload conditions.

Combination therapy has been widely applied in the treatment of complex diseases due to its ability to improve efficacy and reduce drug resistance. In recent years, deep learning techniques have significantly enhanced the accuracy of computational models for predicting drug interactions. However, these methods either focus solely on the molecular structure of drugs and the gene expression of cell lines or consider only the interaction networks related to drugs and cell lines. To effectively explore the combined impact of the structural information of drugs and cell lines and their interaction information in networks on drug synergy prediction, we propose a novel multimodal representation fusion model using hypergraph neural networks, called MoHyperSynergy. MoHyperSynergy constructs a hypergraph based on multimodal representations using the K-nearest neighbors approach. It interacts multimodal representations at the local feature level through an outer product embedding layer and fuses multimodal representations at the global semantic level using a hypergraph neural network, effectively utilizing information from different modalities of drugs and cell lines. MoHyperSynergy simultaneously extracts initial representations from drug molecular structures, cell line gene expressions, and the embeddings of drugs and cell lines in biomedical knowledge graphs as different modalities, and pretrains the model’s representation extractors in a self-supervised manner. We conducted experiments on real-world public datasets and evaluated our model under various scenarios that may arise in practical applications. The experimental results show that MoHyperSynergy achieves excellent performance in predicting drug synergy and significantly outperforms the current state-of-the-art models.

Accurate rigid-body dynamics is crucial for serial industrial robot applications such as force control and physical human-robot interaction. Despite decades of research, the precise identification of dynamic parameters—particularly low-magnitude inertia parameters—remains a challenge for serial industrial robots. Researchers usually focus on developing various parameter estimation methods, while optimizing exciting trajectories in similar ways, typically minimizing the condition number of the information matrix. However, such optimization usually fails to ensure sufficient excitation for each parameter, due to non-convex coupling effects. To address this limitation, we propose a fully decoupled rigid-body dynamics identification (FDRDI) method in this article. This approach innovatively eliminates coupling effects by using novel symmetrical exciting trajectories based on reciprocating S-curve (RSC). This innovation enables the independent identification of dynamic parameters associated with joint friction, as well as the gravity and inertia of links and payloads. Comparative experiments show that FDRDI achieves superior identification accuracy, evidenced by reduced joint torque prediction errors and payload parameter estimation errors.

Gantry cranes are widely used for transporting containers in industry. Lacking in model tests and practical control strategy, the problem that the load suffers swaying due to disturbances such as wind and inertia still exists for spatial multi-rope gantry cranes. In this paper, a scale model of the complete hoisting system is designed and constructed based on a realistic multi-rope gantry crane prototype. Also, considering various constraints in practice such as the non-negative tension in ropes, dynamics of the hoisting system is analysed and a practical anti-sway control strategy is proposed which consists of a robust adaptive controller and a parallel redundant distribution algorithm of rope tension for decoupling. Comparative experiments on the scale model show that the proposed control strategy achieves significant anti-sway effect, and is feasible to be applied in industrial practice.

A large amount of malware families use the domain generation algorithms (DGA) to randomly generate a large amount of domain names. It is a good way to bypass conventional blacklists of domain names, because we cannot predict which of the randomly generated domain names are selected for command and control (C&C) communications. An effective approach for detecting known DGA families is to investigate the malware with reverse engineering to find the adopted generation algorithms. As reverse engineering cannot handle the variants of DGA families, some researches leverage supervised learning to find new variants. However, the explainability of supervised learning is low and cannot find previously unseen DGA families. In this paper, we propose a graph-based semi-supervised learning scheme to track the evolution of known DGA families and find previously unseen DGA families. With a domain relation graph, we can clearly figure out how new variants relate to known DGA domain names, which induces better explainability. We deployed the proposed scheme on real network scenarios and show that the proposed scheme can not only comprehensively and precisely find known DGA families, but also can find new DGA families which have not seen before.