Most current domain adaptation methods for fault diagnosis focus on single target domain. However, test data often comes from multiple target domains, as machines work under different operating conditions, subsequently generating a more complex and extensive distribution of target data. Unfortunately, single target domain adaptation methods are not adaptive for multiple target domains adaptation (MTDA), which results in transfer performance degradation. To this end, a novel disentanglement learning with adaptive centroid alignment is proposed for MTDA. Specifically for disentanglement learning, two encoders and two classifiers are constructed independently for fault-related and domain-related feature extractions and classifications. Followed by the dual-adversarial strategy, only fault-related but domain-irrelevant features are extracted. Furthermore, to achieve the category alignment, we also propose an adaptive centroid alignment strategy, so that the feature centroids of the same fault category in different domains are enforced to be close to each other. Extensive experiments demonstrate the superiority of our proposed method compared with other popular approaches.

Dexterous joints have attracted interest in the field of robotics. This article presents a driving-integrated spherical gear (DISG) that enables entire spherical meshing and active driving between two spherical gears, forming a dexterous multidegrees of freedom rolling contact joint. The DISG consists of a pair of spherical gears and an omnidirectional internal driver. The spherical gear shape is a combined projection of the conventional planar gear profile in the longitudinal and latitudinal directions, which can mesh and be driven over the entire sphere. An actively driving magnet and a passively following magnet are magnetically connected across the spherical gear and together form the internal driver, enabling arbitrary connection points throughout the sphere. In all configurations, one spherical gear can roll in all directions on the surface of the other. Furthermore, we analyze the kinematics of DISG and prove that the DISG-based dexterous joint has good kinematic characteristics, such as singularity-free and full-range workspace. We verify the theoretical and physical characteristics of DISG in a series of experiments on the prototype. We also compare DISG-based joints to other joint actuators and show that DISG-based joints have advantages in dexterity, motion range, compactness, and lightweight.

Rolling contact joints are attracting increasing interest in applications to robotic fingers and manipulators, due to the potential of the absence of abrasion wear, the simplification of the controller, and the enlargement of reachable configurations. This article first proposes a novel two-degree-of-freedom (DOF) spherical rolling contact (SRC) joint, with the joint model elements being formulated, includingrotation matrix,position vector, andfree modes, as with those of classic joints. As an application, a new kind of serial manipulator formed by the SRC joints is presented, and its forward and inverse kinematics are modeled. The motions of the two-DOF SRC joint and manipulator are implemented using the FreeBOT, and the control method is proposed for the FreeBOT, such that the SRC joint and manipulator realize the motion control. The kinematics and control of the two-DOF SRC joint and manipulator are validated using physics simulations and on a real manipulator formed by FreeBOTs.

Energy sharing in modular self-reconfigurable robots ensures the energy balance of the modules, thus allowing the system to work sustainably. This paper proposes an energy sharing mechanism for a novel modular self-reconfigurable robot that allows free connections among modules, termed as FreeBOT, such that each FreeBOT can share energy with peers through surface contact. Corresponding energy sharing rules are proposed to achieve an energy sharing network structure without invalid components. As alternative choices, several types of networks subjected to the above requirements are provided, which also maximize the number of FreeBOTs joining to share energy. We implement and test the prototype of the energy sharing mechanism on FreeBOT. The experimental results show that the mechanism can effectively achieve energy sharing among FreeBOTs.