Current Issue : October-December Volume : 2025 Issue Number : 4 Articles : 5 Articles
Accurate fatigue prediction is essential for ensuring the reliability and durability of engineering systems. Suitable predictive performance was achieved by artificial neural networks trained on the FatLim dataset; however, further improvements are needed due to its small sample size. This study explored the impact of dataset augmentation on model performance by exemplarily expanding the FatLim dataset from 294 to 1732 cases and comparing results against the original dataset. The dataset was augmented by generating additional uniaxial stress scenarios and applying tensor transformations to simulate varied stress orientations. Neural network models were trained separately on the original and expanded datasets, and their predictive performance was evaluated. The results demonstrate that the model trained on the augmented dataset achieved better accuracy, with the mean prediction error decreasing from 0.95% to 0.31% when tested on the original dataset, confirming the effectiveness of dataset expansion in improving fatigue prediction. This research underscores the potential of data augmentation techniques to enhance machine learning models for fatigue analysis....
This study integrated the strengths of ensemble learning and soft computing to develop a future regional rainfall model for evaluating the complex characteristics of island precipitation. Soft computing uses the well-developed adaptive neuro-fuzzy inference system, which has been successfully applied in atmospheric hydrology and combines the features of neural networks and fuzzy logic. This combination enables artificial intelligence (AI) to effectively represent reasoning derived from complex data and expert experience. Due to the multiple atmospheric and hydrological factors that influence rainfall, the nonlinear interrelations among them are highly intricate. Nonlinear principal component analysis can extract nonlinear features from the data, reduce dimensionality, and minimize the adverse effects of data noise and excessive input factors on soft computing, which may otherwise result in poor model performance. Ultimately, ensemble learning enhances prediction accuracy and reduces uncertainty. This study used Tamsui and Kaohsiung in Taiwan as case study locations. Historical monthly rainfall data (January 1950 to December 2005) from Tamsui Station and Kaohsiung Station of the CentralWeather Administration, along with historical and varied emission scenario data (RCP 4.5 and RCP 8.5) from three AR5 GCM models (ACCESS 1.0, CSIRO-MK3.6.0, MRI-CGCM3), were used to evaluate future regional rainfall trends and uncertainties through the method proposed in this study. The research findings indicate the following: (1) Ensemble learning results demonstrate that all examined general circulation models effectively simulate historical rainfall trends. (2) The average rainfall trends under the RCP 4.5 emission scenario are generally consistent with historical rainfall trends. (3) The exceedance probabilities of future rainfall during the mid-term (2061–2080) and long-term (2081–2100) suggest that Kaohsiung may experience precipitation events with higher rainfall than historical data during dry seasons (October to April of next year), while Tamsui Station may exhibit greater variability in terms of exceedance probabilities. (4) Under both the RCP 4.5 and RCP 8.5 emission scenarios, the percentage changes in future rainfall variability at Kaohsiung Station during dry seasons are higher than those during wet seasons (May to September), indicating an increased risk of extreme precipitation events during dry seasons....
The air-handling unit (AHU) is an essential component of heating, ventilation, and air-conditioning (HVAC) systems. Hence, detecting the faults in AHUs is essential for maintaining continuous HVAC operation and preventing system breakdowns. The advent of artificial intelligence has transformed the AHU fault diagnosis techniques. Specifically, deep learning has obviated the necessity for manual feature extraction and selection, thereby streamlining the fault diagnosis process. While conventional convolutional neural networks (CNNs) effectively detect defects, incorporating more spatial variables could enhance their performance further. This paper presents a hybrid architecture combining a CNN model with a long short-term memory (LSTM) model to diagnose the faults in AHUs. The advantages of the LSTM model and convolutional layers are combined to identify significant patterns in the input data, which considerably facilitates the detection of AHU defects. The hybrid design enhances the network’s capability to capture both local and global characteristics, thus improving its ability to differentiate between normal and abnormal circumstances. The proposed approach achieves strong diagnostic accuracy, exhibiting high sensitivity to nuanced fault patterns. Furthermore, its efficacy is corroborated through comparisons with state-of-the-art AHU fault identification techniques....
By integrating visual recognition technology and multi-object recognition into robotic arms, the flexibility and automation of the production process were improved in this study. By applying tiny machine learning (TinyML) and machine vision algorithms, we integrated edge computing devices to control the robotic arms and identified objects precisely on the production line, with ultra-low energy consumption. The developed system in this study included the SparkFun Edge development board and Raspberry Pi Camera Module 3, as edge devices for data processing, image recognition, and robotic arm control. By utilizing the Edge Impulse platform for data collection, model training, and optimization, edge devices and models for use in resource-limited environments were successfully generated. Using Edge Impulse’s automated toolchain, real-time image processing and object recognition were realized. The system achieved improved recognition accuracy and operational speed, demonstrating the potential of TinyML in enhancing the intelligence of robotic arms. MariaDB was chosen for data storage. Grafana was used to design a user-friendly web interface for real-time data monitoring and visualization and immediate data analysis and system monitoring. The developed system presented a success rate of 99% during actual operation. The feasibility of combining advanced image processing technology with robotic arms in intelligent manufacturing was verified in this study. The potential of integrating machine learning and automation technologies was also confirmed for the development of future manufacturing technologies. The model provides a technical reference and ideas for future factories that require high levels of automation and intelligence....
Soft robotics represents a transformative approach to automation, focusing on the development of robots constructed from flexible, compliant materials that mimic biological systems. Being different from traditional rigid robots, soft robots are engineered to adapt and operate efficiently in complex, unstructured environments, making them highly appropriate for applications that require delicate manipulation, safe human–robot interaction, and mobility on unstable terrain. The key principles, materials, and fabrication techniques of soft robotics are explored in this study, highlighting their versatility in industries such as healthcare, agriculture, and search-and-rescue operations. The essence of soft robotic systems lies in their ability to deform and respond to environmental stimuli. The system enables new paradigms in automation for tasks that demand flexibility, such as handling fragile objects, navigating narrow spaces, or interacting with humans. Emerging materials, such as elastomers, hydrogels, and shape-memory alloys, are driving innovations in actuation and sensing mechanisms, expanding the capabilities of soft robots in applications. We also examine the challenges associated with the control and energy efficiency of soft robots, as well as opportunities for integrating artificial intelligence and advanced sensing to enhance autonomous decision-making. Through case studies and experimental data, the potential of soft robotics is reviewed to revolutionize sectors requiring adaptive automation, ultimately contributing to safer, more efficient, and sustainable technological advancements than present robots....
Loading....