A fuzzy neural network (FNN) model is developed to predict the 4-CBA concentration of the oxidation unit in purified terephthalic acid process. Several technologies are used to deal with the process data before modeling.First,a set of preliminary input variables is selected according to prior knowledge and experience. Secondly,a method based on the maximum correlation coefficient is proposed to detect the dead time between the process variables and response variables. Finally, the fuzzy curve method is used to reduce the unimportant input variables.The simulation results based on industrial data show that the relative error range of the FNN model is narrower than that of the American Oil Company (AMOCO) model. Furthermore, the FNN model can predict the trend of the 4-CBA concentration more accurately. 相似文献
Multi‐dimensional data originate from many different sources and are relevant for many applications. One specific sub‐type of such data is continuous trajectory data in multi‐dimensional state spaces of complex systems. We adapt the concept of spatially continuous scatterplots and spatially continuous parallel coordinate plots to such trajectory data, leading to continuous‐time scatterplots and continuous‐time parallel coordinates. Together with a temporal heat map representation, we design coordinated views for visual analysis and interactive exploration. We demonstrate the usefulness of our visualization approach for three case studies that cover examples of complex dynamic systems: cyber‐physical systems consisting of heterogeneous sensors and actuators networks (the collection of time‐dependent sensor network data of an exemplary smart home environment), the dynamics of robot arm movement and motion characteristics of humanoids. 相似文献
This paper presents a tool that enables the direct editing of surface features in large point‐clouds or meshes. This is made possible by a novel multi‐scale analysis of unstructured point‐clouds that automatically extracts the number of relevant features together with their respective scale all over the surface. Then, combining this ingredient with an adequate multi‐scale decomposition allows us to directly enhance or reduce each feature in an independent manner. Our feature extraction is based on the analysis of the scale‐variations of locally fitted surface primitives combined with unsupervised learning techniques. Our tool may be applied either globally or locally, and millions of points are handled in real‐time. The resulting system enables users to accurately edit complex geometries with minimal interaction. 相似文献
The selection of meaningful lines for 3D line data visualization has been intensively researched in recent years. Most approaches focus on single line fields where one line passes through each domain point. This paper presents a selection approach for sets of line fields which is based on a global optimization of the opacity of candidate lines. For this, existing approaches for single line fields are modified such that significantly larger amounts of line representatives are handled. Furthermore, time coherence is addressed for animations, making this the first approach that solves the line selection problem for 3D time‐dependent flow. We apply our technique to visualize dense sets of pathlines, sets of magnetic field lines, and animated sets of pathlines, streaklines and masslines. 相似文献
Splines are useful tools to represent, modify and analyze curves and they play an important role in various practical applications. We present a multiresolution approach to spline curves with arbitrary knots that provides good feature detection and localization properties for non-equally distributed geometric data. In addition, we show how equidistributed data and knot sequences can be efficiently handled using signal processing techniques. 相似文献
Elastomer materials are used in a wide application range and subjected to different loading from which failure of the material results. Because this failure is caused by initiation and propagation of cracks, the application of fracture mechanics methods for the assessment of the material is obvious. A short summary of the methods of technical fracture mechanics including possibilities of determination of crack resistance curves is given. Vulcanizates on the basis of SBR 1500 with various sulfur and carbon black contents were investigated. For describing the crack initiation and crack propagation behavior, several fracture mechanics examination methods were applied. Tear‐analyzer results were used to assess the crack propagation behavior under fatigue‐like loading conditions. Furthermore, for the characterization of the crack resistance of the materials under impact‐like loading conditions, instrumented tensile‐impact tests were performed. To obtain information about the initiation and propagation of a stable crack, quasi‐static fracture mechanics tests were applied. The results of the several tests are discussed in dependence on sulfur and carbon black contents. We found a non‐monotonous behavior of the toughness as a function of carbon black loading. An explanation is given in connection with a percolation‐like transition in filler morphology on larger length scales.
Schematic crack propagation curve for characterizing the fatigue behavior of the vulcanizates recorded in a TFA test. 相似文献