A digital twin of a manufacturing system is a digital copy of the physical manufacturing system that consists of various digital models at multiple scales and levels. Digital twins that communicate with their physical counterparts throughout their lifecycle are the basis for data-driven factories. The problem with developing digital models that form the digital twin is that they operate with large amounts of heterogeneous data. Since the models represent simplifications of the physical world, managing the heterogeneous data and linking the data with the digital twin represent a challenge. The paper proposes a five-step approach to planning data-driven digital twins of manufacturing systems and their processes. The approach guides the user from breaking down the system and the underlying building blocks of the processes into four groups. The development of a digital model includes predefined necessary parameters that allow a digital model connecting with a real manufacturing system. The connection enables the control of the real manufacturing system and allows the creation of the digital twin. Presentation and visualization of a system functioning based on the digital twin for different participants is presented in the last step. The suitability of the approach for the industrial environment is illustrated using the case study of planning the digital twin for material logistics of the manufacturing system.

Significant presence of metallic clutter in minefields results in a high false alarm rate of conventional metal detectors due to their inability to discriminate between metallic parts of a landmine and non-hazardous clutter. In this paper, we present electromagnetic induction (EMI)-based system for identification of small hidden metallic objects. A 1D-convolutional neural network is employed to infer an object class from time-domain magnetic polarizability tensor features. The proposed approach is experimentally validated under laboratory conditions on dataset including two types of landmines and five types of metallic clutter. The model trained on simulations and tested on measurements achieves 98% accuracy (with zero false negatives) for both multi-class and binary “threat or nonthreat” classification problems.

In this article, we investigate a specific search coil tracking problem arising from the use of electromagnetic induction (EMI) sensors to classify buried low metal objects. In the proposed approach, a moving search coil is used as a magnetic field beacon, two triaxial tunnel magnetoresistance (TMR) sensors are used as anchors, and the extended Kalman filter (EKF) is used to estimate five degrees of freedom information on coil’s relative pose. A specific feature of the analyzed application is the pulsed beacon field and the coil’s size comparable to the tracking distance. To address the resulting near-field effects and improve the tracking accuracy, we include a rigorous analytical multiloop model of the search coil into the EKF estimation algorithm and introduce a novel sensor calibration scheme. The system is experimentally validated in realistic dynamic conditions using a handheld pulse induction metal detector as a beacon, and a laboratory-grade optical tracking system with declared sub-millimeter accuracy as a source of ground truth data. For a near-horizontal zigzag scan pattern within a volume of $\sim \,\,40\times 50\times 5$ cm, our system yields mean absolute errors <3 mm for the coil’s x- and $y$ -coordinates, <2 mm for $z$ -coordinates, and <0.5° for the pitch and roll angles, making it a viable solution for pose-referenced EMI sensing.

Industry 4.0 introduces smart solutions throughout the company’s supply chain, including manual assembly, where the goal is to ensure shorter work cycle time, increase productivity and quality, while minimizing costs. Following the principles of this paradigm, this paper proposes a digital transformation of the manual assembly process by implementing a multi-criterial algorithm (MCA) for adjusting and configuring a human-centered smart manual assembly workstation to ensure efficient and ergonomic performance of the manual assembly process. The MCA takes into account various influential parameters, such as the anthropometry of the individual worker, gender, complexity of the assembly process, product characteristics, and product structure. The efficiency of the MCA was verified both in the laboratory environment with the time analysis and in the virtual environment using Digital Human Modelling through several ergonomic analyses. The results of the implementation of the MCA on a manual assembly workstation support the digital (re)design of the manual assembly process with the aim of creating an efficient and ergonomically suitable workstation for each worker, thus increasing the productivity and efficiency of the human-centered manual assembly process.