Journal of Industrial Information Integration最新文献

Human-Machine Interaction (HMI) and Brain-Computer Interface (BCI) are evolving technologies that show the great potentials to extract and utilize humans’ intents in controlling smart machines. However, existing HMI and BCI technologies are limited in terms of (1) the number of Degrees- of-Freedom (DoF) to be controlled and (2) the ways the performance of BCI-enabled control systems are verified and validated. This study aimed to explore the solutions to addree both of above concerns; we proposed a hybrid control system that is capable of training, detecting, and interpreting humans’ intents, and utilizing humans’ intents in real-time controls of smart machines. More specifically, the system acquired brain signals in the form of Electroencephalography (EEG) by an Emotiv Epoc X and processed these signals to detect and extract humans’ intents in real-time machine controls. To cope with the frequency difference of humans’ thinking and machine motion controls, we developed a hybrid control module to fuse humans’ and machine's intelligence so that low-frequency humans’ intents could be used in real-time machine controls. The system was prototyped and verified experimentally. The system was verified to achieve the accuracy of over 90 % in recognizing humans’ intents and controlling a robot by the operator's intents with a satisfactory responding time and accuracy.

The main objective of this article is to provide a framework for intelligent capture-acquisition analysis of geometric information from geological outcrops. By combining deep learning methods with photogrammetric data from unmanned aerial vehicles (UAVs), FPV drones, and terrestrial cameras acquired by a hybrid vision-photogrammetric system (HVPS), intelligent fracture detection and geometric information segmentation of multiscale field geological outcrops were achieved. The extraction results were subsequently used to generate a three-dimensional discrete fracture network (DFN) of real rock masses for studying the influence of the spatial connectivity of discontinuity structural planes on the mechanical and hydrodynamic characteristics of rock masses. By testing data collected in situ from a variety of field rock masses in several regions of China, this framework was shown to be a very efficient method for geostatistical work, exhibiting very low measurement errors. Furthermore, this framework is extremely safe for geologists and applicable to a wide range of site geological environments. It is also suitable for field geological surveys, geometry acquisition of outcropping lithologies, obtaining tunnel face and surrounding fissure statistics, and geological stability assessment of unstable rock masses. This framework can also provide a method for unmanned topographic-geological exploration. Furthermore, the fracture network realism and the data acquisition efficiency have been greatly improved, and the difficulty of developing field measurements and validating the DFN model has been overcome.

Engineering-to-order (ETO) companies satisfy a very demanding market, where each client specifies the type of product they require and actively participate in the design, selection of materials, and other activities. This converts the production processes of ETO companies into one-of-a-kind processes (OKP) type, where production planning and control (PPC) activities are extremely complex. The cause of this complexity is the little or no standardization between the different production cycles that must be executed, as each cycle is of the OKP type. In addition, Intra-logistics operations represent a key factor in ETO PPC, since each piece of work-in-process or sub-assembly can be extremely large, heavy or complicated of handling. Then, ETO systems involve heterogenous production and intra-logistics processes, where the associated information is fragmented and diverse. This hampers a streamline information processing and operations management. To overcome all these issues, a Digital Twin (DT) approach is proposed. The DT designed and developed here allows to integrate engineering and planning departments to be effectively integrated with the shop-floor and operations management in a smooth and effective manner. To solve interoperability and information access without overloading data-entry tasks novel information structures are designed, along with the logical processes that support them. These logical processes enable DT to generate autonomously intra-logistics operations orders from the engineering plans, fostering the system integration and agility. This DT is tested on a manufacturing ETO case study and shows its efficiency.

In the evolving landscape of manufacturing and remanufacturing, assembly lines play a crucial role. Within the context of Industry 5.0, human workers are seen as a valuable and irreplaceable resource. Human-robot collaboration is a promising production model that combines the strengths of human workers and robots, thereby enhancing production efficiency while reducing occupational risks related to ergonomics. Despite these advancements, inherent uncertainties within assembly processes, the integration of human-robot partnerships, and the dynamic nature of market demands pose significant challenges to traditional assembly methods. To address these challenges, this research introduces a novel modelling approach through a mixed-flow assembly line balancing problem designed for uncertain environments, fostering collaboration between humans and robots. The primary goal is to facilitate efficient collaboration within a type-I assembly line balancing problem framework, where predefined assembly beats guide the workflow. In this research, the use of interval type-2 fuzzy sets capabilities was investigated to address uncertainties in the assembly process. Furthermore, the potential of pairing human operators of different abilities with robots of different models for collaborative tasks at workstations was explored, enhancing flexibility and adaptability in the assembly line. In response to the complexity of the problem, this research proposes an efficient multiobjective discrete bees algorithm that incorporates innovative operators and search strategies. Rigorously tested across diverse case studies, this algorithm consistently outperforms other comparator algorithms. This research not only offers novel perspectives on addressing assembly line balancing challenges but also provides valuable insights for the effective implementation of human-robot collaborative assembly in uncertain environments.