The time-varying and multi-dimensional characteristics are major causes of the low performance of soft sensors in chemical processes. To solve the problem, an improved adaptive soft sensor modeling method is proposed....
详细信息
The time-varying and multi-dimensional characteristics are major causes of the low performance of soft sensors in chemical processes. To solve the problem, an improved adaptive soft sensor modeling method is proposed. This method obtains predicted deviation by modular steps of moving window and evaluates deterioration of soft sensors via ttest adaptively. Besides, this paper combines the moving window-autoassociative neural network (AANN) method to update both the modeling auxiliary variable and the auxiliary variable data. data simulation and result analysis obtained via a continuous stirred tank reactor (CSTR) and a debutanizer column process (DCP) show that the improved adaptive soft sensor modeling method proposed in this paper can evaluate the deterioration of soft sensors and update the soft sensor model adaptively, and improve the predicted performance of soft sensors for time-varying and multi-dimensional chemical processes.
In the field of education, there is a gap between research and practice. Lack of data standardization and collection inhibits comparability and generalizability of findings in the context of population heterogeneity. ...
详细信息
Shanghai Central Tower, as China’s landmark super high-rise building, has attracted wide attention since its construction. Because it is much higher than ordinary buildings, it also poses a challenge to construction ...
详细信息
Anaerobic Digestion (AD) technology, known for its waste recycling and environmental clean-up capabilities, also generates renewable energy in the form of biogas. The need to reduce dependence on fossil fuels has exte...
详细信息
ISBN:
(数字)9798350353754
ISBN:
(纸本)9798350353761
Anaerobic Digestion (AD) technology, known for its waste recycling and environmental clean-up capabilities, also generates renewable energy in the form of biogas. The need to reduce dependence on fossil fuels has extensively stimulated interest in this process. The process is known for its complexity, high sensitivity, and potential for instability, which is inherently reflected in the models describing it. Models contain uncertain parameters and highly sensitive to process noise. Parameter identification plays a crucial role during modeling and is a delicate task preceding control law development. It is mandatory to have the best possible estimates of a model that guarantees efficient predictions. This paper focuses on the optimization of stoichiometric and kinetic coefficients of the Acidogenesis Methanogenesis 2 model (AM2). We present in this study the use of the Whale Optimization Algorithm (WOA) to optimize AM2 model parameters and validate the results using data acquired from a Anaerobic Digestion Model $\mathbf{N}^{\circ} 01$ (ADM1). The identification algorithm was implemented in MATLAB 2018. To validate the effectiveness of our proposed approach, we conduct a comparative analysis with Genetic Algorithm (GA). The results, despite certain limitations, underscore the robustness of WOA for parameter estimation.
A highly sensitive analytical method for elemental quantification of U in (Th1-xUx)O-2 mixed oxide (MOX) fuel pellets is extremely necessary for nuclear fuel quality control. It will be an added advantage if the analy...
详细信息
A highly sensitive analytical method for elemental quantification of U in (Th1-xUx)O-2 mixed oxide (MOX) fuel pellets is extremely necessary for nuclear fuel quality control. It will be an added advantage if the analytical method is direct and non-destructive. Presently we have demonstrated a direct non-destructive methodology for (Th1-xUx)O-2 MOX fuel pellets by the X-ray fluorescence technique using U/Th M lines as the analytical line instead of the well resolved U/Th L alpha(1) lines. U/Th M lines were selected as they could be excited using low-energy excitation. In the present study, we have used seven (Th1-xUx)O-2 MOX fuel pellets with varying U/Th concentrations. All the MOX pellets were prepared via the sol-gel micro-sphere pelletization (SGMP) process. All the pellets were presented for mu-XRF measurements. Each pellet was measured at 10 different spots to construct an input data set. Analytical parameters like relative error and precision obtained from the classical FP-based method utilizing U/Th M lines are 22.4% and 4.9%, respectively. To improve the same parameters, we employed a classical chemometric method like partial least square regression (PLSR). It produced the above-mentioned analytical parameters similar to 3.0%. Furthermore, an optimized ANN-based modeling methodology generated a relative error and precision for the U determination in the test sample of 3.1% and 4.9%. The comparative study suggests that both the ANN-based methodology and PLSR outperform the classical FP-based methodology for the analytical quantification of U/Th in MOX by employing U/Th M lines as the analytical line.
Power quality upgrade in grid-connected photovoltaic systems ensures stable and highly efficient operation of modern energy grids. Meanwhile, the high penetration of renewable energy sources brings real challenges to ...
详细信息
The proceedings contain 53 papers. The topics discussed include: the development of a game for cognitive remediation therapy (CRT) to improve attention span and memory among children with learning disabilities;managem...
ISBN:
(纸本)9781665476928
The proceedings contain 53 papers. The topics discussed include: the development of a game for cognitive remediation therapy (CRT) to improve attention span and memory among children with learning disabilities;management of raw material needs and safety stock based on data forecast and system dynamics modeling;understanding user behavior with web session clustering and user engagement metrics;dragonfly algorithm strategy parameters analysis on swarm robot multi-target search efficiency;color-assisted multi-input convolutional neural network for cancer classification on mammogram images;simulation program for modeling temperature distribution in a food dehydrator;statistical assessment for point cloud dataset;investigation of learning rate for directed acyclic graph network performance on dysgraphia handwriting classification;utilization of augmented reality in assisting surgical needle insertion guidance;production and capacity planning as well as inventory and distribution control in snack packaging companies using open source ERP simulation;and parameter-replacement functions for stability-guaranteed variable digital filters.
Multimedia computer labs are an important part of systematic education for universities, and the management and operation of the labs are related to students and computer education. This study analyzes the “Informati...
详细信息
ISBN:
(数字)9798350375336
ISBN:
(纸本)9798350375343
Multimedia computer labs are an important part of systematic education for universities, and the management and operation of the labs are related to students and computer education. This study analyzes the “Information System Success Model” (ISSM) from DeLong & McLean (2003) takes the computer labs of Sanda University as a case study, and collects and analyzes the data from the labs in the past three years to provide big data support for the labs’ operation, and helps to optimize the labs’ resource allocation after the research and analysis of the 6S management model.
Frequent subgraph mining is a fundamental task in the analysis of collections of graphs. While several exact approaches have been proposed, it remains computationally challenging on large graph datasets due to its inh...
详细信息
Stance detection is a Natural Language processing (NLP) task that involves identifying an individual's standpoint on a specific topic and determining their stance as either in favor of or against it. It has variou...
详细信息
暂无评论