Traditional factories are turning into smart factories with the advent of various ICT technologies, and various control decisions are derived by AI technologies. In this circumstance, runtime verification of a control command is important for zero-defect manufacturing processes but challengeable because factories of the future are highly complex and heterogeneous systems. In this paper, we propose DigTwinOps, a Digital Twin framework for Runtime Verification of Cyber-Physical Production Systems (CPPSs). DigTwinOps features a Digital Twin Execution Engine (DTEE) that manages a Digital Twin Model to synchronize states of a real CPPS object in a production environment. With a monitoring and simulation combination process, a human worker can observe the states of the CPPS object and verify the effectiveness of control commands before applying it to a real production environment. The proposed framework is applied to a CPPS prototype production system, and the results show that the framework can work effectively in the controllability verification of control commands.

This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial Revolution and the development of deep learning require deep learning–based problem solving in various fields. Accordingly, various research efforts use deep learning technology to detect errors, such as product defects and diseases, in depth images. However, a depth image expressed in grayscale has limited information, compared with a three-channel image with potential colors, shapes, and brightness. In addition, in the case of tires, despite the same defect, they often have different sizes and shapes, making it difficult to train deep learning. Therefore, in this paper, the four-step process of (1) image input, (2) highlight image generation, (3) image stacking, and (4) image training is applied to a deep learning segmentation model that can detect atypical defect data. Defect detection aims to detect vent spews that occur during tire manufacturing. We compare the training results of applying the process proposed in this paper and the general training result for experiment and evaluation. For evaluation, we use intersection of union (IoU), which compares the pixel area where the actual error is located in the depth image and the pixel area of the error inferred by the deep learning network. The results of the experiment confirmed that the proposed methodology improved the mean IoU by more than 7% and the IoU for the vent spew error by more than 10%, compared to the general method. In addition, the time it takes for the mean IoU to remain stable at 60% is reduced by 80%. The experiments and results prove that the methodology proposed in this paper can train efficiently without losing the information of the original depth data.

As the data rate and area capacity are enormously increased with the advent of 5G wireless communication, the network latency becomes a severe issue in a 5G network. Since there are various types of terminals in a 5G network such as vehicles, medical devices, robots, drones, and various sensors which perform complex tasks interacting with other devices dynamically, there is a need to handle heavy computing resource intensive operations. Placing a multiaccess edge computing (MEC) server at the base station, which is located at the edge, can be one of the solutions to it. The application running on the MEC platform needs a specific simulation technique to analyze complex systems inside the MEC network. We proposed and implemented a simulation as a service (SIMaaS) for the MEC platform, which is to offload the simulation using a Cloud infrastructure based on the concept of computation offloading. In the case study, the Monte-Carlo simulations are conducted using the proposed SIMaaS to select the optimal highway tollgate where vehicles are allowed to enter. It shows how clients of the MEC platform use SIMaaS to obtain certain goals.

This paper presents a new way of data abstraction for visual and haptic representations in immersive analytics using a mid-air haptic display. Visual and haptic abstraction is proposed to transform raw data (wind tunnel data) into another form of data for effective visual and haptic data mapping. Three main features are extracted: (i) Magnitude of Velocity, (ii) Recirculation Region, and (iii) Vorticity. For each feature, visual and haptic abstractions are defined based on data characterization and data reduction. A preliminary study shows a promising direction toward multimodal data interaction in immersive analytics.

This paper proposes a Large Language Model (LLM)-driven framework for generation of Infrastructure as Code (IaC) in dynamic environments. While IaC simplifies infrastructure management, static templates are often inadequate. Leveraging recent LLM advancements, we design and integrate requirements refinement, retrieval-augmented generation (RAG), and code ensemble methods to improve IaC code accuracy. Preliminary results show that, despite challenges(syntax errors and hallucinations), manual adjustments enable executable code, suggesting potential for dynamic generation.