In this work, we propose an optimal control strategy as the unit control for combinedcycle power generation units. Using the same optimal control, we propose to optimize other internal control structures. data-Enabled...
详细信息
In this work, we propose an optimal control strategy as the unit control for combinedcycle power generation units. Using the same optimal control, we propose to optimize other internal control structures. data-Enabled Predictive control is chosen as the optimal control problem formulation, as it does not require a parametric state-space representation of the system. This bypasses the challenging and expensive-to-solve issue of parametric modeling and linearization for highly nonlinear systems. The performance of the controller is investigated in several critical operational scenarios, such as load-following for frequency control and disturbance rejection. Simulation results in Apros, which is an environment dedicated to advanced process simulation, are presented. Copyright (C) 2022 The Authors.
Functional testing stands as a pivotal quality control step in the production process of laptop motherboards, aiming to validate the proper functioning of various components. However, due to the multitude of functiona...
详细信息
ISBN:
(数字)9789887581598
ISBN:
(纸本)9798331540845
Functional testing stands as a pivotal quality control step in the production process of laptop motherboards, aiming to validate the proper functioning of various components. However, due to the multitude of functional modules involved on the motherboard, testing all of them requires a significant amount of time and resources. As a result, production line engineers often rely on empirical selection of modules with low yield rates for testing. However, such empirical yield estimation is often inaccurate. To address this challenge, this study proposes a hybrid model based on XGBoost and Long Short-Term Memory (LSTM) networks to predict the yield of each functional module. By harnessing the feature learning capability of XGBoost and the sequential modeling power of LSTM, this model efficiently explores the intricate correlations among motherboard functional modules, thereby accurately forecasting their yields. We extensively train and validate the model using historical production data and successfully deploy it on real laptop motherboard production lines. Experimental results demonstrate that our hybrid model accurately predicts the yield of each functional module, providing crucial guidance for the functional testing process. Through in-depth analysis of the predicted yield results, engineers can systematically choose testing projects to save time and resources. This research offers a novel approach and pathway for enhancing motherboard production efficiency and quality.
Performing global sensitivity analysis (GSA) can be challenging due to the combined effect of the high computational cost, but it is also essential for engineering decision making. To reduce this cost, surrogate model...
详细信息
ISBN:
(纸本)9783031087578;9783031087561
Performing global sensitivity analysis (GSA) can be challenging due to the combined effect of the high computational cost, but it is also essential for engineering decision making. To reduce this cost, surrogate modeling such as neural networks (NNs) are used to replace the expensive simulation model in the GSA process, which introduces the additional challenge of finding the minimum number of training data samples required to train the NNs accurately. In this work, a recently proposed NN-based GSA algorithm to accurately quantify the sensitivities is improved. The algorithm iterates over the number of samples required to train the NNs and terminates using an outer-loop sensitivity convergence criteria. The iterative surrogate-based GSA yields converged values for the Sobol' indices and, at the same time, alleviates the specification of arbitrary accuracy metrics for the NN-based approximation model. In this paper, the algorithm is improved by enhanced NN modeling, which lead to an overall acceleration of the GSA process. The improved algorithm is tested numerically on problems involving an analytical function with three input parameters, and a simulation-based nondestructive evaluation problem with three input parameters.
Accurate traffic flow forecasting plays a vital role in the effective management and control of intelligent transportation systems. However, existing forecasting methods face constraints due to insufficient informatio...
详细信息
"A blend of engineering & management skills": One of the most affected definitions of process safety management (P.S.M) which focused on preventing major incidents within high hazardous industries (e.g.,...
详细信息
ISBN:
(纸本)9781959025702
"A blend of engineering & management skills": One of the most affected definitions of process safety management (P.S.M) which focused on preventing major incidents within high hazardous industries (e.g., catastrophic accidents, near misses, fires, explosion, toxic gas releases etc.) associated with loss of containment of energy or dangerous substances such as chemical & petroleum products [EL adopted from the ccps/AICHE]. Many incidents are due to inadequate leadership & poor organizational structure while (P.S.M) still focused on physical control, design improvements & engineering solutions. software engineering became one of the engineering solutions represented in embedded system as a good fit, when merging the principles of P.S.M with engineering software a great result will occur to keep the safe operation along time with low frequency & high severity risks. Fusion product is a robot intenerated with microcontroller come with multifunction purposes helping in data logging, analysis & reporting to identify potential hazardous & improve safety protocols. Abstract here is to develop prepared previously autonomous car microcontroller-based with features allow employees to detect, monitor gas leakage serving with this the P.S.M roles especially in oil & gas field, chemical stores & other industries threatening to loss of containment (e.g. liquid petroleum gas (LPG), smoke, other unwanted flammable or toxic gases). Copyright 2024, Society of Petroleum Engineers.
_. This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 213089, “Optimizing Artificial Lift Timing and Selection Using Reduced-Physics Models,” by Hardikkumar Zalavadia, S...
详细信息
_. This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 213089, “Optimizing Artificial Lift Timing and Selection Using Reduced-Physics Models,” by Hardikkumar Zalavadia, SPE, Metin Gokdemir, and Utkarsh Sinha, SPE, Xecta Digital Labs, et al. The paper has not been peer reviewed._. The complete paper presents an artificial lift timing and selection (ALTS) methodology based on a hybrid data-driven and physics-based work flow. The proposed method predicts future unconventional reservoir inflow performance relationship (IPR) consistently and allows for continuous evaluation of ALTS scenarios in unconventional reservoirs with multiple lift types and designs. Continuous use of this process has been shown to improve production, reduce deferred production, and extend the life of lift ***. The intent of the work flow is to maximize the positive economic impact of a well. The authors write that, to their knowledge, incumbent methods do not include the effect of subsurface performance. In the proposed approach, feedback is injected to the reservoir and a closed-loop response is obtained implicitly because of the selection of artificial lift type and operational parameters of that *** hybrid reservoir modeling methodology is based on identifying transient well performance (TWP). The method is based on a novel formulation that combines diffusive time of flight (DTOF), succession of pseudosteady-state material balance, and transient productivity-index (PI) concepts for estimating dynamic reservoir deliverability. (Equations associated with these processes are provided in the complete paper.) This is combined with well-deliverability estimation for different artificial lift methods and their operating parameters to perform continuous nodal analysis and forecast phase rates using novel PI-based forecasting *** analysis. This work establishes a practical method to estimate transient-well PI for every well
Vegetation on the earth's surface affects not only the use of military equipment, but also the process of planning, command and control of operations. Unmanned ground vehicles (UGV) intervene in operations more an...
详细信息
In this research paper, we present the design and implementation of an AI assisted interactive framework for datamodeling and high resolution image synthesis that leverages both state of the art latent diffusion mode...
详细信息
The intermittent slug flow in horizontal circular pipes occurs commonly in industrial applications such as pipeline transportation and nuclear reactor cooling. The phenomenon of elongated bubble centring in slug flow ...
详细信息
In order to analyze and design an ultrasonic motor (USM) control system, an accurate and reliable mathematical model should be established. Due to the nonlinear characteristics of the motor, which are resulted from sp...
In order to analyze and design an ultrasonic motor (USM) control system, an accurate and reliable mathematical model should be established. Due to the nonlinear characteristics of the motor, which are resulted from special structure and complicated working principle, traditional modeling methods are no longer applicable. Nonlinear Hammerstein model structure is proved to be a better choice for describing nonlinearities in operation after years of study and practice. The Hammerstein model of the equivalent circuit model can be established to simulate the process of modeling the actual motor since both of the two models are in a one-to-one correspondence with the motor. In this paper, following the establishment of the equivalent circuit model, a model based on this idea is established with two-phase driving voltage as its inputs. The complete modelingprocess is given and the method is applied to an actual ultrasonic motor, which verifies the effectiveness of the proposed method.
暂无评论