Advanced technologies in modern industry collect massive volumes of data from a plethora of sources, such as processes, machines, components, and documents. This also applies to predictive maintenance. To provide access to these data in a standard and structured way, researchers and practitioners need to design and develop a semantic model of maintenance entities to build a reference ontology for maintenance. To date, there have been numerous studies combining the domain of predictive maintenance and ontology engineering. However, such earlier works, which focused on semantic interoperability to exchange data with standardized meanings, did not fully leverage the opportunities provided by data federation to elaborate these semantic technologies further. Therefore, in this paper, we fill this research gap by addressing interoperability in smart manufacturing and the issue of federating different data formats effectively by using semantic technologies in the context of maintenance. Furthermore, we introduce a semantic model in the form of an ontology for mapping relevant data. The proposed solution is validated and verified using an industrial implementation.

There are several reasons for the development of nanopolymer compounds, such as improving physical, mechanical, and chemical properties, increasing lifespan, reducing costs, and decreasing negative environmental impact. The compatibility of two rubbers and mineral nanofillers in nanocomposites is a challenge that needs to be studied, and the effect of nanofillers on morphological, physical, and mechanical properties should be investigated accordingly. In this study, calcium carbonate nanoparticles were added to a polymer compound that included natural rubber (NR), styrene-butadiene rubber (SBR), vulcanization accelerators, and other additives. For mixing nanoparticles in the polymer matrix, various methods were used, including the solvent method in toluene and W410 solvents and the surface modification of calcium carbonate nanoparticles with stearic acid. The effect of dispersion nanoparticles in nanocomposite specimens on morphology, curing characteristics, and mechanical properties was studied. The morphologies of specimens were determined by X-ray diffraction (XRD) analysis and field emission scanning electron microscopy (FESEM). The particle size of the nanocomposite was approximately 34 nm, and the interlayer spacing between crystal plates increased from 2.81 nm to 3.03 nm. These results indicate a uniform dispersion of nanoparticles, specifically with an optimum content of 3.52%, in the compounds prepared through all mixing methods, with no agglomeration observed in the nanocomposites. The results of the nanocomposites’ curing characterization demonstrate that with the addition of nanoparticles, a strong bond is created in the polymer chains, and curing properties are improved. Among the dispersion methods, the highest percentage improvement in curing properties is observed with the solvent method W410. To evaluate the effect of the addition of calcium carbonate nanoparticles and the dispersion method on improving mechanical properties, tensile, tear, hardness, and rebound resilience tests were performed. In tensile tests, the surface modification method showed the highest enhancement in ultimate stress (80%), followed by the W410 method (64%) and toluene method (63.7%). Tear strength improvements were highest in the W410-solvent sample (80%), followed by the surface modification method (57%) and the solvent-toluene method (50%). The W410 method resulted in the hardest samples, while the surface-modified samples had the lowest hardness. The addition of CaCO3 nanofillers reduced rebound resilience, with the W410 method experiencing the largest reduction (10.64%), followed by the toluene method (6.38%), and with the surface-modified samples showing the lowest reduction (4.25%). The results show that in the W410 solvent method, the nanocomposite is more elastic than for other methods. Additionally, for most of the mechanical properties, the W410 method results in the most growth in improvement.

This study focuses on a musculoskeletal analysis of human lower extremity and associated muscle forces during different rehabilitative tasks and exoskeleton alignment models. By changing the size and orientation of the impairment levels that could be caused by the misalignment of the exoskeleton and biological knee joint, muscle stress variations were observed. This indicates an increase in force such as that generated by the Vastus lateralis muscle up to 4.3% due to a 5 mm lateral offset from an anatomically healthy knee joint location. In another setting, while a subject moved the shank through a circular trajectory using an exoskeleton support, muscle strain due to misalignment was reflected at the rectus femoris with a variation of 44%, the biceps femoris large head with 32% and the gastrocnemius muscles with 31–33% variation. These results suggest that misalignment should be taken into account while using exoskeletons with certain trajectories for knee rehabilitation purposes. Based on the shortcomings of conventional physiotherapeutic tasks, the outcome of this study can be helpful in prescribing an impactful yet convenient configuration toward a safe and promising rehabilitation process. Assessment of exoskeleton alignment during rehabilitation is important to ensure user safety with a better therapy efficacy.

This study is aimed at reviewing the various literature on the robot-based rehabilitation and the associated technical issues, augmentation, utilization, and safeties. During recent years, Biorobotics and Collaborative Robots have played a remarkable role to provide fast, accurate and efficient therapy and assistance. Most of these robots are equipped with various types of devices to control the intensity, duration, and precision of the training while some feedback systems have also been used to monitor the efficiency of the process and help physicians and therapists to furnish a high quality treatment. Haptic devices, Electromyography (EMG)/Electroencephalography (EEG) sensors, virtual environment and other interactive approaches have been utilized to optimize the process and to investigate different mental as well as physiological aspects. This review paper provides a comprehensive background on the human robot interactions and their outcomes in medical settings and potential research areas in the domain.

Hand and wrist function is commonly assessed using qualitative clinical tests that provide limited objective information and data in motor performance over time. Advances in haptic technology and machine learning provide new opportunities to develop more quantitative approaches. In this study, we developed a quantitative circle-tracing assessment using a haptic pen. The primary objective was to use unsupervised machine learning to compare low performance and high-performance repetitions to determine if there were significant differences in variability. Twenty-nine healthy participants completed 40 circle-tracing repetitions while positional data were recorded and converted into tracing error metrics. Circle drawing was performed with constrained upper arm and wrist. Tracing performance was analyzed using sliding-window percentage-change calculations and a Bayesian Gaussian Mixture Model (BGMM) built into K-fold Cross Validation to identify stable clusters representing high-performance, low-performance, and neutral states. The proposed framework successfully identified significant performance fluctuations across multiple time intervals. High-performance trials were detected at 90% probability, whereas low-performance trials were identified at a greater probability (98%). Comparing the two cases, low-performance detection demonstrated less variability across short- and long-term evaluation windows, with higher agreement across multiple window sizes. In contrast, high-performance detection exhibited greater variability. Both high and low-performance detections were most reliable (97.5% and 99.7%, respectively) during short-term assessments. These findings suggest that declines in performance are more readily distinguishable than performance improvements when using error-based circle-tracing metrics. The results demonstrate the feasibility of combining haptic assessment with unsupervised machine learning to objectively characterize circle-tracing performance. This approach has potential to improve diagnosis and rehabilitation monitoring by providing quantitative measures.

Mobile-robot navigation policies have typically assumed a fixed sensing input and robot platform. In this work, we investigate a teacher–student policy where teachers learn continuous velocity commands from LiDAR-based Twin Delayed Deep Deterministic Policy Gradient, and the student navigates using either LiDAR or camera observations. The student has two modalities with separate feature extractors. The extracted features and robot-state variables are fed into a shared encoder and actor, which map them to linear and angular velocity commands. The generalized two-platform configuration includes a Robot-ID token of scalar type. Training and evaluation were performed in ROS-Gazebo using simulated Pioneer 3-DX and TurtleBot3 Waffle robots. Robot-ID conditioning increased generalized LiDAR success to 90.4% on Pioneer 3-DX and to 91.2% on TurtleBot3 Waffle, up from 71.8% and 79.5%, and camera-based success was 87.3% and 84.0%, respectively. Across four controlled LiDAR-to-vision handover conditions, we achieved an overall success rate of 88.8-90.8%. Overall, 85.2-90.1% of the episodes that were still active at the planned switch were completed without resetting or retraining the policy. The results demonstrate that the conditioning on robot identity is very helpful for cross-platform LiDAR performance and that the shared student policy is able to continue navigation after external scheduling of the active sensing branch. The results provide a controlled, simulation-based feasibility assessment of the proposed policy architecture and establish the basis for subsequent physical robot validation.