Manufacturing companies increasingly become “smarter” as a result of the Industry 4.0 revolution. Multiple sensors are used for industrial monitoring of machines and workers in order to detect events and consequently improve the manufacturing processes, lower the respective costs, and increase safety. Multisensor systems produce big amounts of heterogeneous data. Data fusion techniques address the issue of multimodality by combining data from different sources and improving the results of monitoring systems. The current paper presents a detailed review of state-of-the-art data fusion solutions, on data storage and indexing from various types of sensors, feature engineering, and multimodal data integration. The review aims to serve as a guide for the early stages of an analytic pipeline of manufacturing prognosis. The reviewed literature showed that in fusion and in preprocessing, the methods chosen to be applied in this sector are beyond the state-of-the-art. Existing weaknesses and gaps that lead to future research goals were also identified.

This paper presents a method to detect and identify damage in a laboratory offshore wind turbine support structure. The structure consists of three different parts: the jacket, the tower and the nacelle. The jacket is a lattice structure joined with several bolts. The tower consists of three different sections joined by bolts. The nacelle is composed of a single piece. The different parts are also joined with bolts. The damage in the structure is simulated by loosening some of the bolts in the jacket. Two damage detection algorithms, namely AutoRegressive methods and NullSpace methods, have been tested in a primitive variation of this structure without the jacket, obtaining good results. In this paper we present the application of the last damage detection method to the new structure with the jacket and an extension to identification of the damage.

In the present paper, we introduce an application of two damage detection methods to a laboratory structure. One of the methods is based on autoregressive modeling of the signals involved, whereas the second one is based on subspace identification. Both have been tested in a tower that simulates a wind turbine. The results obtained are correct for the damages simulated by loosening some bolts of the different joints. The results show that the second method is computationally more efficient whereas the results are more stable in the first one.

This paper is devoted to derive some sufficient conditions for the existence and uniqueness of positive solutions to a singular second-order dynamic equation with Dirichlet boundary conditions.