No abstract

No abstract

The bubble size distribution at the froth surface of a flotation cell is closely related to the process condition and performance. The flotation performance can be reasonably predicted through continuous measuring the bubble size distribution by a machine vision system. In this work a new watershed algorithm based on whole and sub-image classification techniques is introduced and successfully validated by several laboratory and industrial scale froth images taken under different process conditions. The results indicate that the developed algorithms, in particular the sub-image classification based segmentation algorithm, can accurately and reliably identify the individual small and large bubbles in the actual froth images, which is often problematic.

No abstract

No abstract

Substantial progresses have been made over the past decade in using machine vision for automatic control of the froth flotation process. A machine vision system is able to extract the visual features from the captured froth images and present the results to process control systems. The current research work is concerned with the development and implementation of a machine vision system for real time monitoring and control of a batch flotation system. The proposed model-based control system comprises two in-series models connecting the process variables to the froth features and the metallurgical parameters along with a stabilizing fuzzy controller. The results indicate the developed machine vision based control system is able to accurately predict the metallurgical parameters of the existing batch flotation system from the extracted froth features and efficiently maintain them at their setpoints despite step disturbances in the process variables. Furthermore, the proposed control system leads to higher target values for the metallurgical parameters than the previously developed system (RCu = 91.1 % ; GCu = 11.2% vs. RCu = 87.6 % ; GCu = 8.1%).

It is a well-known fact in literature and practice that flotation froth features are closely related to process conditions and performance. The authors have already developed some reliable algorithms for measurement of the froth surface visual parameters like bubble size distribution, froth color, velocity and stability. Furthermore, the metallurgical parameters of a laboratory flotation cell were successfully predicted from the extracted froth features.In this research study the fuzzy c-mean clustering technique is utilized to classify the froth images (collected under different process conditions) based on the extracted visual characteristics. The classification of the images is actually necessary to determine the ideal froth structure and the target set-points for a machine vision control system. The results show that the captured froth images are well-classified into five categorizes on the basis of the extracted features. The correlation between the visual properties of froth (in different classes) and the metallurgical parameters is discussed and modeled by the Downloaded by [University of Sussex Library] at 13:54 28 June 20162 Adaptive Neuro-Fuzzy Inference System (ANFIS). The promising results illustrate that the performance of the existing batch flotation system can be satisfactorily estimated from the measured froth characteristics. Therefore, the outputs from the current machine vision system can be inputted to a process control system.

Automatic control of the flotation process is a difficult task due to the large number of variables involved, significant disturbances, and the process's complex nature. Previous research has established that flotation performance is reflected in the structure of the froth's surface. This paper describes the application of machine vision and fuzzy logic in controlling a batch-flotation cell. To perform this process, a laboratory flotation cell was operated under different conditions while process and image data were simultaneously recorded. Then, correlations between the resultant froth features and process variables were modeled, and an interpretable froth model was created. A fuzzy controller was designed and implemented to control process performance through the extracted froth features at the desired level by manipulating the selected process variables. The results indicate that the developed control system is able to handle process disturbances and track reference signals.