Development of a vision‐based online soft sensor for oil sands flotation using support vector regression and its application in the dynamic monitoring of bitumen extraction

Abstract

Extraction from oil sands is a crucial step in the industrial recovery of bitumen. It is challenging to obtain online measurements of process outputs such as bitumen grade and recovery. Online measurements are a prerequisite for innovating better process control solutions for process efficiency and cost reduction. We have developed a soft sensor to provide online measurements of bitumen grade and recovery in a flotation‐based oil sand extraction process. Continuous froth images were captured using a VisioFroth camera system on a batch flotation unit. A support vector regression (SVR) model with a Gaussian kernel was constructed to develop a soft sensor for bitumen grade and recovery using froth image features as the inputs. The model was trained and validated for batch flotation of different grades of oil sands ore at industry‐relevant process conditions. A Dean‐Stark analyzer was used to obtain offline grade and recovery measurements that were used to calibrate the soft sensor. Mean squared errors (MSE) of 62 and 74 were achieved for grade (%) and recovery (%), respectively, and this was obtained using 5‐fold cross validation. The developed soft sensor model has been applied successfully in the real‐time dynamic monitoring of flotation grade and recovery for different grades of ore and operating conditions.

Metrological Advantages of Applying Vibration Analysis to Pipelines: A Review

“…Popular linear machine learning approaches in soft metrology are Multiple Linear Regression (MLR) [39] [47] and Gaussian Process Regression (GPR) [40] [38]. In nonlinear regression, some of the alternatives are Support Vector Regression (SVR) [48], K Nearest Neighbor (KNN) regression [49] and Extreme Learning Machine (ELM) [50] [51].…”

Soft sensor of iron tailings grade based on froth image features for reverse flotation

“…Computer vision and image processing technology have been applied in many fields. Many scholars have applied machine vision to the flotation of nonferrous metal minerals and nonmetallic materials such as coal and silica sand (Fu and Aldrich, 2019; Lin et al, 2018; Massinaei et al, 2019; Popli et al, 2018; Vinnett and Alvarez-Silva, 2015; Xu et al, 2016). Some (Massinaei et al, 2019) applied computer vision technology to flotation columns in a coal preparation plant.…”

2019 Winner of The Canadian Journal of Chemical Engineering Award for Best Graduate Student Paper

“…This work has been tested on various applications, including mineral and oil sands flotation. Currently, he is working at Teck Resources Ltd. as a Process Control Engineer/Specialist, where he has been developing regulatory and advanced process control frameworks for milling processes …”