data-driven modeling techniques have been widely applied in industrial systems for process monitoring. However, these models heavily rely on data accuracy and completeness. Challenges emerge when the mode characterist...
详细信息
ISBN:
(数字)9798350349252
ISBN:
(纸本)9798350349269
data-driven modeling techniques have been widely applied in industrial systems for process monitoring. However, these models heavily rely on data accuracy and completeness. Challenges emerge when the mode characteristics of the system alter due to equipment deterioration (such as heat exchanger fouling, component wear, catalyst deactivation) or after maintenance activities (like cleaning, repair, replacement, etc.). data collected from the old mode (before the mode change) no longer accurately reflects the characteristics of the new mode (after the mode change). This presents a significant challenge for multimode processmodeling, as the new mode model cannot directly utilize old mode data when there is insufficient training data for the new mode. To address this issue, we propose a novel transfer learning-based multi-fidelity modeling (TL-MFM) method. The key innovation of this method lies in its fusion of limited high-fidelity data from the new mode with sufficient low-fidelity data from the old mode to construct a robust monitoring model. By leveraging a model transfer framework that optimizes the transfer of relevant information across fidelity levels, the TL-MFM method enhances the adaptability of the monitoring model. The effectiveness of the TL-MFM method is validated through a case study on a real-world condenser in a steam turbine generator set.
Today's real time computers activities and applications required data services in the distributed platform where real time applications have been needed for databases, in which data and operations have special cha...
详细信息
Background: Focus-exposure process window measurement and analysis is an essential function in lithography, but the current geometric approach suffers from several significant deficiencies. Aim: By clearly identifying...
详细信息
ISBN:
(纸本)9781510649828;9781510649811
Background: Focus-exposure process window measurement and analysis is an essential function in lithography, but the current geometric approach suffers from several significant deficiencies. Aim: By clearly identifying the problems with the Geometric process Window approach, a new process window measurement and analysis method will be proposed to address these problems. Approach: The Probabilistic process Window proposed here takes metrology uncertainty into account and rigorously calculates the expected fraction of in-spec features based on settings for best dose/focus and presumed random errors in dose and focus. Using the fraction of in-spec features thus calculated, a much more rigorous determination of the trade-off between exposure latitude and depth of focus can be performed. Results: The Probabilistic process Window approach is demonstrated on focus-exposure data generated from a standard extreme ultraviolet lithography process at three different pitches, showing the value of this method. Conclusions: The new Probabilistic process Window approach offers clear advantages in accuracy for both depth of focus determination and best dose/focus determination. Consequently, its use is preferred both for process development applications and high-volume manufacturing.
Aiming at the commutation failure problem after removing receiving end three phase short circuit fault of HVDC system, this paper expounds the power angle oscillation process and power angle oscillation characteristic...
详细信息
processcontroller performance evaluation systems have been widely used in modern industries with increasingly complex control objects. However, there is a prerequisite for their implementation: the models obtained fr...
详细信息
This paper proposes a phase compensation method for rapid parameter identification aimed at addressing the hysteresis problem in the digital twin parameter identification of BUCK converters. Based on collected BUCK ci...
详细信息
ISBN:
(数字)9798350351330
ISBN:
(纸本)9798350351347
This paper proposes a phase compensation method for rapid parameter identification aimed at addressing the hysteresis problem in the digital twin parameter identification of BUCK converters. Based on collected BUCK circuit data, this method performs Hilbert transformations on the data from both the physical model and the digital twin model. It calculates the phase difference between the two and mitigates the error caused by actual sampling data through phase compensation. This process reduces computational redundancy resulting from errors, enabling timely parameter updates in the digital twin model. Additionally, a BUCK converter digital twin platform is designed for experimental verification. The experimental results demonstrate that, while ensuring accuracy, this method effectively enhances the parameter identification speed of the digital twin model, facilitating subsequent field-circuit coupling analysis..
Nowadays, surveys show that the cooling system accounts for 30% of the energy consumption of data centers. The challenge of designing an effective cooling control system to minimize data center energy consumption cost...
详细信息
In this brief paper, a data-based method on the fault diagnosis in aero-engine transmission systems is developed. Firstly, during the operation of splines, we acquire the acceleration vibration signal. We process the ...
详细信息
This research delves into examining the forecast of air quality in Coimbatore, India, according to data gleaned from the Central Pollution control Board (CPCB) specific to the area. The gathered information underwent ...
详细信息
ISBN:
(数字)9798350376913
ISBN:
(纸本)9798350388473
This research delves into examining the forecast of air quality in Coimbatore, India, according to data gleaned from the Central Pollution control Board (CPCB) specific to the area. The gathered information underwent a preprocessing step, using interpolation to ensure uniformity and completeness. Forecasting methods such as Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SARIMAX) and Long Short-Term Memory (LSTM) models were utilized to predict air quality levels. The SARIMAX model was fine-tuned through a grid search process, while the LSTM underwent hyperparameter adjustments to improve air quality predictions. Performance evaluation of these models involved metrics like R-squared, Mean absolute error, and Root mean square error. Based on the selected evaluation criteria, the outcome shows that SARIMAX outperformed LSTM in Coimbatore when it came to predicting the air quality. This analysis improves our understanding of air quality patterns in Coimbatore. Highlights SARIMAX's effectiveness as a modeling tool for atmospheric science applications.
Aiming at the complexity of abnormal risk identification of active customers' safe power consumption, this paper proposed a clustering analysis method for abnormal risk identification of active customers' safe...
详细信息
暂无评论