Known classes aware and emerging unknown classes rejection based on adversarial training for open set fault diagnosis.

Most domain adaptation diagnosis approaches presume that the label spaces of different domains are identical. However, novel fault states may emerge in real-world applications, and traditional closed-set approaches only rely on marginal distribution alignment, making them difficult to resolve the open-set domain adaptation issue. One typical open-set problem is that the label spaces of the source and target domains are partially overlapped. To tackle this issue, this paper proposes an approach called known classes aware and emerging unknown classes rejection (KAEUR) based on adversarial training. First, an adaptive weighted learning scheme based on the entropy is introduced to the maximum classifier discrepancy method, which aims to align the target known-type samples with each class of the source known-type samples and suppress the influence of unknown-type samples during feature alignment, thereby extracting domain-invariant features through interactive adversarial training. Second, two binary cross-entropy schemes and the entropy modules are constructed to enhance the divergence between the known and unknown types. Then, an integrated criterion is established to reject the target unknown classes. Finally, three machinery datasets are constructed to demonstrate the effectiveness and superior performance of the proposed approach.

Three-Dimensional Vibration Model of Cylindrical Shells via Carrera Unified Formulation.

In this paper, we present a novel and unified model for studying the vibration of cylindrical shells based on the three-dimensional (3D) elastic theory and the Carrera Unified Formulation. Our approach represents a significant advancement in the field, as it enables us to accurately predict the vibrational behavior of cylindrical shells under arbitrary boundary conditions. To accomplish this, we expand the axial, circumferential, and radial displacements of the shell using Chebyshev polynomials and Taylor series, thereby reducing the dimensionality of the expansion and ensuring the precision and rigor of our results. In addition, we introduce three groups of artificial boundary surface springs to simulate the general end boundary conditions of the cylindrical shell and coupling springs to strongly couple the two surfaces of the cylindrical shell φ = 0 and φ = 2π to ensure continuity of displacements on these faces. Using the energy function of the entire cylindrical shell model, we obtain the characteristic equation of the system by finding the partial derivatives of the unknown coefficients of displacement in the energy function. By solving this equation, we can directly obtain the vibration characteristics of the cylindrical shell. We demonstrate the convergence, accuracy, and reliability of our approach by comparing our computational results with existing results in the literature and finite element results. Finally, we present simulation results of the frequency features of cylindrical shells with various geometrical and boundary parameters in the form of tables and figures. Overall, we believe that our novel approach has the potential to greatly enhance our understanding of cylindrical shells and pave the way for further advancements in the field of structural engineering. Our comprehensive model and simulation results contribute to the ongoing efforts to develop efficient and reliable techniques for analyzing the vibrational behavior of cylindrical shells.