Semiconductor fabrication is regarded as one of the most complicated production processes with a high-mixed and uncertain production context, and it suffers from tool failures. Prognostics can predict the time when a ...
详细信息
Semiconductor fabrication is regarded as one of the most complicated production processes with a high-mixed and uncertain production context, and it suffers from tool failures. Prognostics can predict the time when a process tool cannot perform its intended function. Therefore, preventive maintenance can be planned in time with the minimum impact on the production lines. Because most of the tool faults cannot be owed to the failure of a single component, it is challenging to model the system directly through mechanism analysis. Therefore, the development of failure prognostics in semiconductor manufacturing is somewhat impeded. data-driven approaches are appropriate in this case, especially when the domain knowledge of the system under study is not comprehensive enough. This article attempts to propose a novel data-driven prognostic method integrated with the auto-associative regression and the Gaussian process to address the issue. This proposed method can extract the failure factors, establish the prognostic model and present the reliability of the model. On the basis of the built prognostic model, the failure tendency is predicted and the maintenance schedule can be determined. The validity and feasibility of the proposed method are demonstrated through a numerical example and a practical semiconductor manufacturing process, respectively. The proposed prognostic scheme can guide the frequency plan of preventive maintenance in the fabrication process and improve the productivity in semiconductor manufacturing.
Software process Model (SPM) is an abstraction of the software development process over time to assist in managing the process. SPM has attracted significant attention from researchers and practitioners in the past de...
详细信息
ISBN:
(纸本)9798400709913
Software process Model (SPM) is an abstraction of the software development process over time to assist in managing the process. SPM has attracted significant attention from researchers and practitioners in the past decades. Due to the complexity of SPM, building a practical process model often requires collaboration between academia and industry. Unfortunately, there are few empirical studies on SPM conducted in collaboration with enterprises. In this paper, we report on the challenges and solutions encountered while modeling software processes based on our collaboration with a global enterprise. These experiences are valuable to both researchers and practitioners. We presented the modelingprocess in detail and collected all the interview records during collaboration. As a result of building an SPM in the enterprise, we identify seven challenges and discussed solutions for each of them. The fundamental issue with SPM remains the quality and availability of data, even within industry settings. To enhance the value and applicability of models, we propose a checklist for building simulation models. The checklist can be used by modelers and practitioners to verify details that are easily overlooked during the modelingprocess. Our experience report provides a practical reference with researchers and practitioners who are interested in modeling software process.
We consider the problem of finding control-oriented models for the electrode resistance of submerged arc furnaces (SAF) to aid the metallurgical processcontrol of ferrosilicon production. To accomplish this goal, we ...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
We consider the problem of finding control-oriented models for the electrode resistance of submerged arc furnaces (SAF) to aid the metallurgical processcontrol of ferrosilicon production. To accomplish this goal, we analyze the field data gathered from the Norwegian metal producer Wacker AS, which are the most important input parameters for accurately predicting electrode resistances. This is done by investigating the predictive capabilities of different linear and non-linear model structures in different furnace operating conditions, and discussing which type of non-linearity induces the best-performing models both in terms of prediction fit and modeling error in opportune test sets. We finally provide interpretations of why the presence of this non-linearity results in the best performance by connecting their structure with domain expertise about the electrical dynamics within SAF circuits.
While conducting large-depth vertical drilling, correcting well trajectory deviations is a critical and challenging task. Designing a feasible deviation-correction trajectory becomes an expensive constrained multi-obj...
详细信息
While conducting large-depth vertical drilling, correcting well trajectory deviations is a critical and challenging task. Designing a feasible deviation-correction trajectory becomes an expensive constrained multi-objective optimization problem due to the need for refined modeling of large-depth wellbore stability analysis. There is a pressing need for advanced drilling trajectory planning methods designed to handle robust constraints and to consider refined geological formation modeling, as current surrogate model-assisted optimization algorithms lack efficiency and balance among feasibility, convergence, and diversity. A Gaussian process-assisted Bayesian Multi-Objective Evolutionary Algorithm (MOEA) based on the reference point-based Non-dominated Sorting Genetic Algorithm (NSGA-III) is developed to manage the expensive wellbore stability objective. While surrogate models can effectively mitigate the computational expense, they may not adequately satisfy the stringent trajectory planning constraints. To enhance the constraint handling ability, an intricately devised infill criterion, Feasibility-oriented Bi-objective Acquisition Function (FBAF), tends to select promising feasible solutions to infill into the next generation. The deviation-correction trajectory planning simulation experiment was carried out under limited evaluations with real vertical well data. The results of empirical attainment function analysis demonstrate that the proposed FB-NSGA-III reduces the number of evaluations and exhibits superior performance compared to 11 other traditional surrogate-assisted MOEAs, particularly in terms of feasibility. FB-NSGA-III successfully prevents the back-hook by avoiding constraint violations and maintaining curvature within the specified safety and directional drilling tool build-up range.
A residual deep reinforcement learning (RDRL) based on an approximate-model-driven optimization approach is proposed for inverter-based volt-var control (IB-VVC) in active distribution networks. A modified Markov deci...
详细信息
A residual deep reinforcement learning (RDRL) based on an approximate-model-driven optimization approach is proposed for inverter-based volt-var control (IB-VVC) in active distribution networks. A modified Markov decision process is introduced to formulate the model-based and RDRL-based IB-VVC simultaneously, and then RDRL learns a residual action based on the action of the model-based approach with an approximate model. It inherits the control capability of the approximate-model-based optimization and enhances the policy optimization capability by residual policy learning. Since the approximate model acquired by operators is generally relatively reliable, the action solved by model-based optimization approaches is not far away from the optimal one. This allows RDRL to search for the residual action in a smaller residual action space, which further improves the approximation accuracy of the critic and reduces the search difficulties of the actor. Simulations demonstrate that RDRL improves the optimization performance considerably throughout the learning stage and verifies their three rationales for superior performance point-by-point on 69 and 141 bus balanced distribution networks.
Sintering process is a strongly coupled multi-variable nonlinear system with large lag and initial sensitivity. It contains control target with less manipulate variables than controlled variables, and the phase transi...
详细信息
ISBN:
(纸本)9798350366907;9789887581581
Sintering process is a strongly coupled multi-variable nonlinear system with large lag and initial sensitivity. It contains control target with less manipulate variables than controlled variables, and the phase transitions vary frequently and severely during operation. For that, this paper demonstrated novel description with pattern-moving methodology for the sintering process of nonlinear dynamical system that is an integrated method including pattern recognition and improved generalized cell mapping (GCM). The pattern class variable was first proposed to describe a class of complex systems with motion statistical characteristics. Because of the pattern class variable is not calculated directly, an improved measurement approach combined GCM with Autoregressive Integrated Moving Average (ARIMA) was put forward and applied in actual industrial scene. At last, simulation experiments with real data are completed, which revealed the availability and feasibility of the proposed scheme.
The development of next-generation battery management systems needs models with enhanced performance to enable advanced control, diagnostic, and prognostic techniques for improving the safety and performance of lithiu...
详细信息
ISBN:
(纸本)9798350382662;9798350382655
The development of next-generation battery management systems needs models with enhanced performance to enable advanced control, diagnostic, and prognostic techniques for improving the safety and performance of lithium-ion battery systems. Specifically, battery models must deliver efficient and accurate predictions of physical internal states and output voltage, despite the inevitable presence of various system uncertainties. To facilitate this, we propose a lightweight hybrid modeling framework that couples a high-fidelity physics-based electrochemical battery model with a computationally-efficient Gaussian process regression (GPR) machine learning model to predict and compensate for errors in the electrochemical model output. This is the first time that GPR has been implemented to predict the output residual of an electrochemical battery model, which is significant for the following reasons. First, we demonstrate that GPR is capable of considerably improving output prediction accuracy, as evidenced by an observed average root-mean-square prediction error of 7.3 mV across six testing profiles, versus 119 mV for the standalone electrochemical model. Second, we employ a data sampling procedure to exhibit how GPR can use sparse training data to deliver accurate predictions at minimal computational expense. Our framework yielded a ratio of computation time to modeled time of 0.003, indicating ample suitability for online applications.
This paper proposes a data-driven modeling method for aircraft by predicting model errors and optimizing model structures. Based on flight test data from the mechanism model, the aircraft data-driven model is establis...
详细信息
ISBN:
(纸本)9798350334722
This paper proposes a data-driven modeling method for aircraft by predicting model errors and optimizing model structures. Based on flight test data from the mechanism model, the aircraft data-driven model is established by several trained basic neural networks for fitting dynamics relationships of aircraft and recurrent neural networks for compensating for model errors. Compared to the traditional data-driven modeling method, this method can more effectively avoid and solve the problem of instability of data-driven models with disturbances at long running times. Finally, the proposed method's feasibility and the established model's credibility are verified by simulation experiments with complex disturbance and statistical analysis for model accuracy.
In this work, the activities of a chemical industry enterprise were investigated using statistical dataanalysis methods. The purpose of the study is to evaluate and develop recommendations for improving the efficienc...
详细信息
ISBN:
(纸本)9798350395839;9798350395846
In this work, the activities of a chemical industry enterprise were investigated using statistical dataanalysis methods. The purpose of the study is to evaluate and develop recommendations for improving the efficiency of the enterprise. To achieve the goal, the following tasks were performed: a predictive assessment of the enterprise's performance indicator was carried out;using multidimensional correlation and regression analysis, the factors influencing this indicator were analyzed;a simulation model of the work of the structural unit of the enterprise was developed and analyzed. The relevance of the study is justified by the possibility of applying its results in practice in order to optimize and improve the efficiency of the enterprise.
As the classical analytics in the field of data-driven fault monitoring, time neighborhood preserving embedding (TNPE), dynamic inner canonical correlation analysis (DiCCA), and slow feature analysis (SFA) provided th...
详细信息
As the classical analytics in the field of data-driven fault monitoring, time neighborhood preserving embedding (TNPE), dynamic inner canonical correlation analysis (DiCCA), and slow feature analysis (SFA) provided three different choices for characterizing time-serial variation inherent in sequential samples. Considering the unsupervised nature of these three algorithms as well as their variants, it could be more appropriate to jointly exploit time-serial variation from multiple perspectives in a comprehensive manner. This recognition then motivates us to propose a novel dynamic modeling algorithm titled as joint time-serial variation analysis (JTSVA) for fault monitoring. The proposed JTSVA aims to extract dynamic latent variables (DLVs) with respect to a joint integration of time-manifold embedding, latent auto-regressive, and slow-varying capabilities own by TNPE, DiCCA and SFA, respectively. Furthermore, an additional orthogonality constraint is further assigned to the problem definition of JTSVA, so that the extracted DLVs could have enhanced discriminant in uncovering valuable information for satisfactory fault monitoring performance. Finally, the superiority of JTSVA in fault monitoring, in terms of false alarm rate and fault detection rate, is validated through comparative experiments on two industrial-scale examples, i.e., the Tennessee Eastman benchmark process and a real-world multiphase flow facility.
暂无评论