Rolling bearings are the core components of mechanical and electrical systems. A practical fault diagnosis scheme is the key to ensure operational safety. There are excessive characteristic parameters with remarkable randomness and severe signal coupling in the rolling bearing operation, which makes the fault diagnosis to be challenging. To deal with this problem, the Gramian angular field (GAF) and DenseNet are combined to perform feature extraction and fault diagnosis. The GAF can convert 1-dimensional time series into an image, which can guarantee the completeness of feature information without temporal dependence. The GAF images are then trained by using the DenseNet to generate a data set network. In this process, the transfer learning (TL), which can solve the problem of insufficient samples, is integrated to the DenseNet to enhance its extensibility. The comparative simulations are carried out to illustrate the effectiveness of the proposed method.

Parafoil trajectory directly affects the power generation of a high-altitude wind power generation (HAWPG) device. Therefore, it is particularly important to optimize the parafoil trajectory and then to track it effectively. In this paper, the trajectory of the parafoil at high altitudes is optimized and tracked in a comprehensively parameterized manner. Both the complex dynamic characteristics of the parafoil and the dexterous demand of the high-altitude controller are considered. Firstly, the trajectory variables and control signals are parameterized as Lagrange polynomials in terms of the corresponding values at the selected nodes. Then, the Radau pseudospectral method (PSM) is employed to reformulate the original dynamic trajectory optimization problem into a static nonlinear programming (NLP) problem. By doing so, the parameterized optimal trajectory, which has the maximum net power generation, can be obtained. To attenuate the strong nonlinear, multivariable and coupling characteristics of the flexible parafoil, a bandwidth parameterized linear extended state observer (ESO) is used to estimate and reject these dynamics explicitly in a unified way. Finally, the simulation results demonstrate the effectiveness of the proposed parameterized trajectory optimization and control strategies. The main contribution of this study is that complicated nonlinear parafoil dynamics with a complex trajectory can be well regulated by a PID-type linear time-invariant controller, which is appealing for practitioners.

Efficient Trajectory Planning and Tracking Control for Underactuated Crane