To address the problems of existing 2D image-based imbalanced fault diagnosis methods for rolling bearings, which generate images with inadequate texture details and color degradation, this paper proposes a novel image enhancement model based on a dual-branch generative adversarial network (GAN) combining spatial and frequency domain information for an imbalanced fault diagnosis of rolling bearing. Firstly, the original vibration signals are converted into 2D time–frequency (TF) images by a continuous wavelet transform, and a dual-branch GAN model with a symmetric structure is constructed. One branch utilizes an auxiliary classification GAN (ACGAN) to process the spatial information of the TF images, while the other employs a GAN with a frequency generator and a frequency discriminator to handle the frequency information of the input images after a fast Fourier transform. Then, a shuffle attention (SA) module based on an attention mechanism is integrated into the proposed model to improve the network’s expression ability and reduce the computational burden. Simultaneously, mean square error (MSE) is integrated into the loss functions of both generators to enhance the consistency of frequency information for the generated images. Additionally, a Wasserstein distance and gradient penalty are also incorporated into the losses of the two discriminators to prevent gradient vanishing and mode collapse. Under the supervision of the frequency WGAN-GP branch, an ACWGAN-GP can generate high-quality fault samples to balance the dataset. Finally, the balanced dataset is utilized to train the auxiliary classifier to achieve fault diagnosis. The effectiveness of the proposed method is validated by two rolling bearing datasets. When the imbalanced ratios of the four datasets are 0.5, 0.2, 0.1, and 0.05, respectively, their average classification accuracy reaches 99.35% on the CWRU bearing dataset. Meanwhile, the average classification accuracy reaches 96.62% on the MFS bearing dataset.
An active damping control technique based on improved linear active disturbance rejection control (LADRC) is suggested to address the inadequate damping of doubly fed induction generator (DFIG) systems coupled to the grid using series compensation capacitors. Conventional LADRC still has certain limitations under complicated operating conditions, primarily because of its inadequate periodic disturbance estimate capabilities, which limit the system’s dynamic performance and disturbance-rejection capability. An enhanced LADRC scheme is created for the inner current loop of the rotor-side converter (RSC) in the DFIG system in order to lessen these restrictions. To enable a real-time estimate and adjustment of sub-synchronous disturbances, a decoupled linear extended state observer (LESO) is first proposed. In order to effectively attenuate both sub-synchronous oscillation and periodic disturbances, a composite control structure with enhanced suppression capability is constructed by incorporating an improved repetitive control scheme into the linear state error feedback law. The results show that the improved LADRC significantly enhances damping performance and disturbance rejection capability in the subsynchronous frequency range, suppressing active power oscillations within approximately 0.3 s based on a ±10% settling band. Compared with the conventional LADRC, the average THD of the grid current is reduced from 3.43% to 0.56%.
In this paper, stabilization problems for a particular class of non linear continuous model with time-delays in the form of Takagi-Sugeno(TS) are investigated. The considered models are of multiple time-delays in state. Some new sufficient conditions for stability and stabilizability are given. They are based on some PDC control laws and some matrix translation properties. First of all, we derive stability conditions of unforced and forced system of considering model, respectively. We then discuss stabilization problem with two cases: (i) unknown delays and (ii) known delays, and give stabilization conditions via LMI. All given conditions are in the form of LMI's and it's easy to be checked by means of MATLAB. Finally, two examples are worked out to illustrate the theory.
An integral sliding mode control method is presented for a class of nonlinear systems. The control design is divided into two steps. Firstly, a linear system is derived from the original complicated system, and an asymptotically stable controller is designed for this simplified system using linear system design method. Secondly, based on the stable closed-loop linear system, an integral sliding surface is constructed, and a control is developed to ensure the reachability of the sliding surface. Consequently, the stabilization of the whole complicated system is achieved. The stability of the closed-loop system is also analyzed. Finally, simulation studies are included to illustrate the effectiveness of the proposed method.