Multivariate statistical monitoring of the aluminium smelting process

A Soft Sensor Approach Based on an Echo State Network Optimized by Improved Genetic Algorithm

In the process of fault diagnosis and the health and safety operation evaluation of modern industrial processes, it is crucial to measure important state variables, which cannot be directly detected due to limitations of economy, technology, environment and space. Therefore, this paper proposes a data-driven soft sensor approach based on an echo state network (ESN) optimized by an improved genetic algorithm (IGA). Firstly, with an ESN, a data-driven model (DDM) between secondary variables and dominant variables is established. Secondly, in order to improve the prediction performance, the IGA is utilized to optimize the parameters of the ESN. Then, the immigration strategy is introduced and the crossover and mutation operators are changed adaptively to improve the convergence speed of the algorithm and address the problem that the algorithm falls into the local optimum. Finally, a soft sensor model of an ESN optimized by an IGA is established (IGA-ESN), and the advantages and performance of the proposed method are verified by estimating the alumina concentration in an aluminum reduction cell. The experimental results illustrated that the proposed method is efficient, and the error was significantly reduced compared with the traditional algorithm.

Towards the Integration of Mobile Augmented Reality within an Aluminium Process Fault Detection and Diagnosis System

Mobile Augmented Reality (AR), which mixes the real world and the virtual world on hand-held devices, is a growing area of the manufacturing industry. Since mobile AR can be used to augment a users view of an industry plant, it provides alternative solutions for design, quality control, monitoring and control, service, and maintenance in complex process industries, such as the aluminium smelting industry. The objective of this paper is to discuss the integration of mobile AR within an aluminium industrial plant, in order to achieve effective fault detection and diagnosis. The possible integration of mobile AR within an aluminium fault detection and diagnosis system is shown with regard to four main functions, namely (1) plant information system, (2) fault history, (3) interactive troubleshooting, and (4) statistical analysis results. This paper opens up possible future works, where the potential use of mobile AR can be explored as an additional user interface component, for increasing the effectiveness of process monitoring within the aluminium smelting process.