With increasing complexity of industrial processes, a number of variables are becoming increasingly large in modeling and monitoring steps, which is particularly prominent in dynamic processes. To address the issue of...
详细信息
With increasing complexity of industrial processes, a number of variables are becoming increasingly large in modeling and monitoring steps, which is particularly prominent in dynamic processes. To address the issue of information redundancy in dynamic processes, this study proposes a sparse dynamic matrix estimation method (SDMEM) based on joint sparse constraints, which can effectively remove the irrelevant process variables and implement a more flexible structure for a dynamic process. Accordingly, the problem that dynamic features are difficult to extract owing to the high sampling rate is effectively solved by introducing differential information. Furthermore, a fast iterative optimization algorithm is designed for the proposed SDMEM with differential information (SDMEM-DI). A theoretical analysis shows the superiority of the proposed optimization algorithm in reducing computational complexity. Finally, experiments are conducted on a numerical example, a continuous stirred tank reactor (CSTR), and a catalytic cracking unit data of a refining and chemical plant, and the results show the effectiveness of the proposed SDMEM-DI.
The integration of semisupervised modeling and discriminative information has been sporadically discussed in the research literature of traditional classification modeling, while the former one would make full use of ...
详细信息
The integration of semisupervised modeling and discriminative information has been sporadically discussed in the research literature of traditional classification modeling, while the former one would make full use of the collected data and the latter one would further improve the classification performance. In this article, the Hessian semisupervised scatter regularized classification model is proposed as a coherent framework for the nonlinear process classification upon both labeled and unlabeled data. It is innovatively designed with a loss function to evaluate the classification accuracy and three regularization terms, respectively, corresponding to the geometry information, discriminative information, and model complexity. Both cases of the coherent framework, respectively, casted to the reproducing kernel Hilbert space and linear space, enjoy a theoretically guaranteed analytical solution. Experiments on process classification tasks on a benchmark dataset and a real industrial polyethylene process illustrate the merits of the proposed method in a sense that the class information of novel collected data is accurately predicted.
In order to solve the problem that it is difficult for traditional methods to effectively analyze the generation and propagation process of large-scale cascading failures in power grid macroscopically, a power network...
详细信息
This paper investigates the generation of realistic processdata by utilizing adversarial networks to emulate actual steel process information. The objective is to create data resembling processdata without discernib...
详细信息
In this article, a finite-horizon optimal trajectory control strategy is developed for near space hypersonic vehicle (NSHV) longitudinal model with multi-constraints including external disturbance, system modeling err...
详细信息
In this article, a finite-horizon optimal trajectory control strategy is developed for near space hypersonic vehicle (NSHV) longitudinal model with multi-constraints including external disturbance, system modeling error, and input saturation. The whole controlprocess has two parts: inner-loop attitude control and outer-loop trajectory control. First, the feedback linearization method is applied to design a tracking controller for outer-loop system, and reference signals for inner-loop attitude control can be obtained using Newton iteration method. Second, for the inner-loop attitude system with multi-constraints, a finite-horizon optimal tracking control scheme consists of feedforward control input and adaptive dynamic programming based optimal feedback controller is designed. In this way, not only the adverse effects of above multi-constraints are eliminated, but also the optimally tracking performances are guaranteed. Finally, the Lyapunov analysis method is utilized to ensure the stability of the entire closed-loop control system, and simulation tests with respect to NSHV longitudinal trajectory tracking are supplied to verify the availability of the proposed strategy. In this paper, a finite horizon optimal trajectory control strategy is developed for near space hypersonic vehicle. Not only the optimal tracking performance are guaranteed, but also the multi-constraints including external disturbance, system modeling error and input saturation are ***
In the present study, dynamic modeling, optimal operation and control of a reactive batch distillation process is illustrated based on experimental and simulation studies using methyl acetate production case study. An...
详细信息
In the present study, dynamic modeling, optimal operation and control of a reactive batch distillation process is illustrated based on experimental and simulation studies using methyl acetate production case study. An equilibrium stage model, incorporating non ideal VLE and start-up region of heating, is developed based on data generated on an experimental unit by identifying five input parameters representing uncertainties. The optimal control problem is solved using genetic algorithm, considering the objective function identified on the basis of trend analysis using the developed dynamic model, to find the optimal reflux ratio, heat input to the reboiler, and mole ratio of methanol to acetic acid in the initial reaction mixture. Open-loop and closed-loop implementations clearly illustrate the improved performance with respect to the quantity of methyl acetate in the distillate product with a reasonably high conversion and product purity within reasonably short batch duration, illustrating the successful optimal control implementation experimentally.& COPY;2023 Institution of Chemical Engineers. Published by Elsevier Ltd. All rights reserved.
The additive-manufacturing (AM) field necessitates a robust process-monitoring system for quality assurance and control. To meet this industrial requirement, quality-evaluation models have emerged as powerful tools fo...
详细信息
The additive-manufacturing (AM) field necessitates a robust process-monitoring system for quality assurance and control. To meet this industrial requirement, quality-evaluation models have emerged as powerful tools for providing quality feedback. Recently, convolutional-neural-network- (CNN)-based classification models have gained popularity in quality evaluation using image data. However, such models require sufficient image data for training, a requirement that is challenging to fulfill in the context of metallic AM due to the complexity of decomposition and analysis. This challenge is particularly pronounced in start-up or medium-sized metallic-AM enterprises. Moreover, many countries around the world have faced a decline in population and a shortage of labor in the engineering field. This growing shortage of workers to collect datasets exacerbates this challenge. In this study, experiments of directed-energy-deposition (DED) processes for single-line and single-track metallic deposition using AISI 316 L stainless-steel powders were conducted with two experimenters. After the process, a minimal amount of cross-sectional surface image data of the metallic deposition was binary-processed and analyzed across three quality states: normal state, surface burrs, and internal defects. To compensate for the lack of training data, multiple strategies are proposed, including image preprocessing and ResNet transfer learning. The selection of an optimization solver and layer depth for maximizing classification performance was discussed. The potential performance of ResNet dealing with binary images and performance standards with few training data was also identified by comparing with other higher-level architectures (Inception and Xcepition).
Electrical conduction within the context of transformer oil stands as a dynamic and effective method widely employed in the research area of electrical engineering, specifically power systems. In this paper, we presen...
详细信息
ISBN:
(纸本)9798350349740;9798350349757
Electrical conduction within the context of transformer oil stands as a dynamic and effective method widely employed in the research area of electrical engineering, specifically power systems. In this paper, we present and develop an innovative numerical model based on the finite element method to study and analyze electrical conduction in transformer oil. Our model simulates the oil's volumetric conduction process under high voltages, which facilitates the calculation of electrical field and potential distributions. To ensure the robustness and reliability of our numerical model, we undertake a systematic exploration by investigating the impact of various process parameters on shaping the conduction process in transformer oil, along with the analysis of temperature distribution and the effect of the electro-hydrodynamic (EHD) instability of the transformer oil on its electrical quantities.
Reasoning about distance is indispensable for establishing or avoiding contact in manipulation tasks. To this end, we present an online approach for learning implicit representations of signed distance using piecewise...
详细信息
Reasoning about distance is indispensable for establishing or avoiding contact in manipulation tasks. To this end, we present an online approach for learning implicit representations of signed distance using piecewise polynomial basis functions. Starting from an arbitrary prior shape, our method incrementally constructs a continuous and smooth distance representation from incoming surface points, with analytical access to gradient information. The underlying model does not store training data for prediction, and its performance can be balanced through interpretable hyperparameters such as polynomial degree and number of segments. We assess the accuracy of the incrementally learned model on a set of household objects and compare it to neural network and Gaussian process counterparts. The utility of intermediate results and analytical gradients is further demonstrated in a physical experiment.
To accurately predict the key parameters of the municipal solid waste incineration (MSWI) process, this paper proposes an improved case-based reasoning (CBR) predictive modeling method based on a deep Q network to rea...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
To accurately predict the key parameters of the municipal solid waste incineration (MSWI) process, this paper proposes an improved case-based reasoning (CBR) predictive modeling method based on a deep Q network to realize the case adaptation process. First, the MSWI operation process is analyzed to screen out the relevant feature variables and build the corresponding case base. Second, the K-nearest neighbor (KNN) algorithm is used to realize the case retrieval process of the parameter prediction, and cases similar to the current incineration state are obtained. Then, based on the "Learning-Evaluation-Revision" idea, the case difference adaptation knowledge between similar cases and the feature variables of the current state is learned through the deep Q network to realize key parameter prediction. Finally, the actual data of a solid waste incineration plant are used to predict the key parameters of the furnace temperature and flue gas oxygen content. The results show that the proposed method can accurately predict the MSWI process parameters.
暂无评论