As Digital Twins gain more traction and their adoption in industry increases, there is a need to integrate such technology with machine learning features to enhance functionality and enable decision making tasks. This has lead to the emergence of a concept known as Digital Triplet; an enhancement of Digital Twin technology through the addition of an ’intelligent activity layer’. This is a relatively new technology in Industrie 4.0 and research efforts are geared towards exploring its applicability, development and testing of means for implementation and quick adoption. This paper presents the design and implementation of a Digital Triplet for a three-floor elevator system. It demonstrates the integration of a machine learning (ML) object detection model and the system Digital Twin. This was done to introduce an additional security feature that enabled the system to make a decision, based on objects detected and take preliminary security measures. The virtual model was designed in Siemens NX and programmed via Total Integrated Automation (TIA) portal software. The corresponding physical model was fabricated and controlled using a Programmable Logic Controller (PLC) S7 1200. A control program was developed to mimic the general operations of a typical elevator system used in a commercial building setting. Communication, between the physical and virtual models, was enabled using the OPC-Unified Architecture (OPC-UA) protocol. Object recognition using “You only look once” (YOLOV3) based machine learning algorithm was incorporated. The Digital Triplet’s functionality was tested, ensuring the virtual system duplicated actual operations of the physical counterpart through the use of sensor data. Performance testing was done to determine the impact of the ML module on the real-time functionality aspect of the system. Experiment results showed the object recognition contributed an average of s to an overall signal travel time of s.
8 March 2023 in International Journal of Precision Engineering and Manufacturing
Viewpoint selection for Structure from Motion has historically split into two paradigms: Camera Network Design (CND), which optimizes sensor configurations offline against a prior object model by propagating pixel uncertainty into 3D covariance, and Next Best View (NBV) planning, which sequentially selects viewpoints online from an occupancy representation built during acquisition. Though each has begun borrowing from the other, both still aggregate reconstruction criteria across the entire object, limiting scalability for geometrically complex targets.This work bridges the two by localizing sensor placement to depth-map-derived Regions of Interest (ROIs), fusing CND’s prior-driven uncertainty modeling with NBV’s targeted, region-scoped efficiency. For each ROI, a bi-objective NSGA-II formulation jointly maximizes inter-view feature-matching consistency and minimizes triangulation uncertainty via an A-optimality criterion, subject to photogrammetric and geometric constraints. Pareto-efficient configurations, selected via pseudo-weighting, were evaluated through a full photogrammetric reconstruction pipeline of a rendered crashed car model against a uniformly sampled baseline. All three pseudo-weight configurations outperformed the baseline in reconstruction accuracy and point-cloud density using only 22 viewpoints versus 71, demonstrating that combining CND’s covariance-optimal rigor with NBV’s localized efficiency yields more information-dense acquisitions than exhaustive uniform sampling, with applications to forensic documentation, stockpile estimation, and archaeological recording.