The goal of unsupervised domain adaptation aims to utilize labeled data from source domain to annotate the target-domain data, which has none of the labels. Existing work uses Siamese network-based models to minimize the domain discrepancy to learn a domain-invariant feature. Alignment of the second-order statistics (covariances) of source and target distributions has been proven an effective method. Previous papers use Euclidean methods or geodesic methods (log-Euclidean) to measure the distance. However, covariances lay on a Riemannian manifold, and both methods cannot accurately calculate the Riemannian distance, so they cannot align the distribution well. To tackle the distribution alignment problem, this paper proposes mapped correlation alignment (MCA), a novel technique for end-to-end domain adaptation with deep neural networks. This method maps covariances from Riemannian manifold to reproducing kernel Hilbert space and uses Gaussian radial basis function-based positive definite kernels on manifolds to calculate the inner product on reproducing kernel Hilbert space, and then uses Euclidean metric accurate measuring the distance to align the distribution better. This paper builds an end-to-end model to minimize both the classification loss and the MCA loss. The model can be trained efficiently using backpropagation. Experiments show that the MCA method yields the state-of-the-art results on standard domain adaptation data sets.

With the development of IoT technology, the digital twin has been applied in many fields. It is the key to realizing the integration of physical information space and an effective means for intelligent upgrading of products, providing a novel idea for the whole life cycle management of complex products. As a pillar industry at the national strategic level, the shipbuilding industry is in the stage of informatization transformation and upgrading and needs to improve its own competitiveness. The ship whole life cycle includes design, construction, operation, and maintenance, as well as scrapping and recycling, but each stage has a certain independence, which makes it prone to the problem of information islands. However, the current research on the product full lifecycle digital twin has not yet considered the impact of historical data of successive generation products on each stage of the current product lifecycle. To address the above issues, this paper firstly proposes the vertical–horizontal design idea from the perspective of the product whole life cycle and combining historical experience (vertical) with real-time data (horizontal) to realize the construction and evolution of digital twin models at all stages of the life cycle. Then, on the basis of the vertical–horizontal design idea, a framework for the ship whole life cycle digital twin is proposed. Finally, the operation mechanism of the framework is elaborated from the four stages of the ship life cycle, with a view to providing a reference for the transformation and upgrading of the future ship industry.