With the recent digitization, electronic equipment housings are required to be thin-walled and have rigidity, heat dissipation, corrosion resistance, and electromagnetic shielding properties. Magnesium alloys are prom...
详细信息
In devising an effective Hazard Identification, Risk Assessment and Determining Controls plan of a company, it is crucial to understand the factors that relate with the Inherent and Residual Risks to prioritize the im...
详细信息
industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineeringsystems. However, existing prognostic models for systems with multiple...
详细信息
industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineeringsystems. However, existing prognostic models for systems with multiple failure modes face several challenges in real-world applications, including overlapping degradation signals from multiple components, the presence of unlabeled historical data, and the similarity of signals across different failure modes. To tackle these issues, this research introduces two prognostic models that integrate the mixture (log)-location-scale distribution with deep learning. This integration facilitates the modeling of overlapping degradation signals, eliminates the need for explicit failure mode identification, and utilizes deep learning to capture complex nonlinear relationships between degradation signals and residual useful lifetimes. Numerical studies validate the superior performance of these proposed models compared to existing methods.
Background/Context: Recent laws to ensure the security and protection of personal data establish new software requirements. Consequently, new technologies are needed to guarantee software quality under the perception ...
详细信息
This article introduces differentially private log-location-scale (DP-LLS) regression models, which incorporate differential privacy into LLS regression through the functional mechanism. The proposed models are establ...
详细信息
This study delves into the utilization of Generative Adversarial Networks (GANs) for generating subject-specific time series sensor data, offeringaninnovativealternativetotraditionalmetamodel-basedsimulations. We unde...
This study delves into the utilization of Generative Adversarial Networks (GANs) for generating subject-specific time series sensor data, offeringaninnovativealternativetotraditionalmetamodel-basedsimulations. We undertake an in-depth analysis of DoppelGANger, a prominent GAN variant for time series data and metadata generation, evaluating its efficiency and efficacy. The sensor data for this investigation was sourced from the National Health and Nutrition Examination Survey, which served as the foundational training set. We scrutinized the synthesized sensor data corresponding to various physical attributes, focusing on the temporal and multi-dimensional statistical properties. Our empirical findings underscore the potential of GANs to adeptly capture the time-dependent correlations and the intricate statistical characteristics inherent in multi-dimensional data. This insight into GANs’ capabilities is a crucial step towards more sophisticated synthetic data generation, with significant implications for future applications in wearable technology and personalized health monitoring systems.
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of...
详细信息
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a 2D navigation task. We show how the use of animal videos improves performance over RL algorithms that do not leverage such observations.
One of the key emerging technologies in Industry 4.0 is the Digital Twin (DT). Although it promises increased efficiency, productivity, and innovation, its adoption faces challenges such as high investment costs and t...
详细信息
One of the key emerging technologies in Industry 4.0 is the Digital Twin (DT). Although it promises increased efficiency, productivity, and innovation, its adoption faces challenges such as high investment costs and the need for workforce requalification. Generative Artificial Intelligence (GAI) emerges as a promising solution, offering capabilities to accelerate development processes and reduce costs. This study aims to leverage GAI to enhance the development of DT and support decision-making in industrial environments by proposing a Generative Assistant for Digital Twin Simulations (GADTS). This proposal generates operational models quickly, offers greater customization, and facilitates the creation of efficient scenario simulations in natural language. The proposal was tested with artificial data. As a result, the development of highly personalized DT simulations with Key Performance Indicators (KPIs) was entirely abstracted into natural language requests.
Radio frequency energy harvesting has attracted considerable interest as a technique of enabling self-powered wireless networks. This technique faces several challenges, such as the receiving and the rectifying module...
详细信息
This work presents a performance comparison between the newly developed Manta Ray Foraging Optimization (MRFO) and two different variants created for tuning a decentralized fractional order proportional-integral-deriv...
This work presents a performance comparison between the newly developed Manta Ray Foraging Optimization (MRFO) and two different variants created for tuning a decentralized fractional order proportional-integral-derivative (FOPID) controller for a multiple-input multiple-output (MIMO) application. The application consists of a ball mill pulverizing system to pulverize coal and maximize fuel efficiency. MRFO and its applications have the task of finding the optimal controller variable values to control the system's temperature and pressure. The MRFO is a metaheuristic based on the behavior of manta rays, and although it shows efficient performance it may be improved through the use of techniques which generate new variants of the algorithm. Two techniques were used in the de-velopment of new variants: Quantum mechanics and opposition-based learning. The three different versions of MRFO were used to minimize a custom fitness function which is a combination of the integral time squared error (ITSE) and the overshoot of the system response. Simulations were carried using Simulink and Matlab softwares. For analyzing the performances, statistical measures such as minimum, maximum, best, mean, median, and standard deviation of the fitness function over 50 runs were used. Additionally, the different variants were also compared for minimizing 10 benchmark functions. The results show that the use of the previously mentioned techniques improve the performance of the original MRFO in optimizing the FOPID to control the ball mill pulverizing system.
暂无评论