Factor-Based Industrial Process Prediction

Author(s):  
Jun Zhao ◽  
Wei Wang ◽  
Chunyang Sheng
2021 ◽  
Vol 2095 (1) ◽  
pp. 012037
Author(s):  
Ting Shi ◽  
Wu Yang ◽  
Junfei Qiao

Abstract Nonlinear systems widely exist in all fields of industrial production and are difficult to model because of complex non-linearity. Neural network is widely used in process prediction, fault detection and fault diagnosis of modern industry because of the nonlinear fitting ability. Due to various structures, there exists diversity in the performance of neural networks. However, only the appropriate network can improve the efficiency and safety in modelling nonlinear industrial process, which requires full consideration of the structure of neural network. In this study, several typical structures of neural networks are compared and analysed, and the performance differences caused by these structures are presented in detail. Finally, performance differences of neural networks with inconsistent structures are verified on several experiments. The results showed that neural networks with inconsistent structures were good at dealing with different types of nonlinear systems. Our work will provide a theoretical basis in accurately modeling the industrial production process, which is beneficial to nonlinear system control.


Author(s):  
C. Claire Thomson

The first book-length study in English of a national corpus of state-sponsored informational film, this book traces how Danish shorts on topics including social welfare, industry, art and architecture were commissioned, funded, produced and reviewed from the inter-war period to the 1960s. For three decades, state-sponsored short filmmaking educated Danish citizens, promoted Denmark to the world, and shaped the careers of renowned directors like Carl Th. Dreyer. Examining the life cycle of a representative selection of films, and discussing their preservation and mediation in the digital age, this book presents a detailed case study of how informational cinema is shaped by, and indeed shapes, its cultural, political and technological contexts.The book combines close textual analysis of a broad range of films with detailed accounts of their commissioning, production, distribution and reception in Denmark and abroad, drawing on Actor-Network Theory to emphasise the role of a wide range of entities in these processes. It considers a broad range of genres and sub-genres, including industrial process films, public information films, art films, the city symphony, the essay film, and many more. It also maps international networks of informational and documentary films in the post-war period, and explores the role of informational film in Danish cultural and political history.


2000 ◽  
Vol 627 ◽  
Author(s):  
Gabriel Popescu ◽  
Aristide Dogariu

ABSTRACTIn many industrial applications involving granular media, knowledge about the structural transformations suffered during the industrial process is desirable. Optical techniques are noninvasive, fast, and versatile tools for monitoring such transformations. We have recently introduced optical path-length spectroscopy as a new technique for random media investigation. The principle of the method is to use a partially coherent source in a Michelson interferometer, where the fields from a reference mirror and the sample are combined to obtain an interference signal. When the system under investigation is a multiple-scattering medium, by tuning the optical length of the reference arm, the optical path-length probability density of light backscattered from the sample is obtained. This distribution carries information about the structural details of the medium. In the present paper, we apply the technique of optical path-length spectroscopy to investigate inhomogeneous distributions of particulate dielectrics such as ceramics and powders. The experiments are performed on suspensions of systems with different solid loads, as well as on powders and suspensions of particles with different sizes. We show that the methodology is highly sensitive to changes in volume concentration and particle size and, therefore, it can be successfully used for real-time monitoring. In addition, the technique is fiber optic-based and has all the advantages associated with the inherent versatility.


Author(s):  
Antonio Dourado ◽  
Paulo Barbeiro ◽  
Edgar Ferreira ◽  
Jorge Henriques ◽  
Maria Antonio ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document