This paper introduces the Virtual manufacturing Platform (VMP), a cloud-complete educational platform targeting manufacturing industries providing tutorials and sandboxing. The scope of this paper focuses on the robot...
详细信息
In this paper we perform analysis on Pravega distributed streaming storage with and without connection pooling. When connection pooling is enabled, there will be a restriction of number of open connections for data tr...
详细信息
In order to study the effect of laser cutting process parameters on the slit width of garbage bags made of polyethylene (PE) material, Box-Behnken test was designed to test the cutting of polyethylene film using a 30 ...
详细信息
An important point for the widespread dissemination of FAIR-data is the lowest possible entry barrier for preparing and providing data to other scientists according to the FAIR criteria. If scientists have to manually...
详细信息
This article provides analysis data for Transformer Diagnostics Monitor (TDM) based Transformer and autotransformer monitoring systems manufactured by Dimrus, Russia. Some disadvantages and advantages of installing su...
详细信息
Large language models (LLMs), such as ChatGPT, have demonstrated remarkable capability in question answering but face challenges when it comes to knowledge-based rea-soning, such as limited training data and hallucina...
详细信息
Software modeling requires a challenging combination of expertise in both domain knowledge and modeling formalisms. Existing methods often fail to provide effective, general modeling assistance. This research introduc...
详细信息
ISBN:
(纸本)9798400706226
Software modeling requires a challenging combination of expertise in both domain knowledge and modeling formalisms. Existing methods often fail to provide effective, general modeling assistance. This research introduces a novel approach using large language models (LLMs) to enhance software modeling. Utilizing few-shot prompt learning, our method supports various modeling activities without extensive training data. Initially focusing on static and behavioral formalisms like UML diagrams, we aim to extend this to other paradigms and integrate it into the Model-Driven engineering (MDE) pipeline. Additionally, we aim to assess productivity, model quality, and accuracy when receiving real-time, context-aware suggestions during modeling tasks.
The integration of Industrial Internet of Things (IIoT) sensors and devices into traditional manufacturing environments offers significant benefits in terms of efficiency, adaptability, and data-driven decision-making...
详细信息
Wire arc additive manufacturing (WAAM) utilizes conventional welding processes and wire-feedstock to deposit material layer by layer until a near net-shape geometry has been achieved. This approach gives WAAM great po...
详细信息
ISBN:
(纸本)9780791888100
Wire arc additive manufacturing (WAAM) utilizes conventional welding processes and wire-feedstock to deposit material layer by layer until a near net-shape geometry has been achieved. This approach gives WAAM great potential among metal additive manufacturing processes for its ability to produce larger scale components much faster than powder-based processes. The selection of certain initial WAAM process parameters, such as input power and interlayer dwell time, can often impact the stability of the contact-tip-to-workpiece distance (CTWD), current, voltage, and linear energy density during deposition. The resulting process stochasticity can cause variations in part geometry, microstructure, and mechanical properties. Therefore, it is desirable to create process models that can predict these WAAM process condition values for a variety of initial process parameter settings. These predictions can then be used to optimize initial WAAM process parameter settings or forecast when process condition instability is expected to occur. In the present work, single- bead multi-layer walls are deposited using a variety of input power and interlayer dwell time settings. Two different modeling approaches are then investigated: multilayer perceptron (MLP) regression and time series forecasting. An artificial neural network (ANN) is trained to predict process condition values based on the initial WAAM process parameters and a given time in the deposition process. Autoregressive integrated moving average (ARIMA) and longshort term memory (LSTM) time series models are trained to forecast subsequent process condition values based solely on the previous process condition values with no prior knowledge of the initial WAAM process parameters. The models are evaluated and compared based on their accuracy in predicting data streams of CTWD, current, voltage, and linear energy density. Additionally, the effect of training data quantity on model accuracy is examined for each model approach. F
Digital Twins allow for designing, operating, and optimizing running systems by replicating the operations of the physical components in a digital environment. Interconnectivity between Digital Twin models and corresp...
详细信息
暂无评论