On the optimization of froth flotation by the use of an artificial neural network

Al-Thyabat, S.

doi:10.1016/s1006-1266(08)60087-5

Cited by 55 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimization was the main topic of a paper written by Al-Thyabat (2008). The influence of three input parameters (feed mean particle size, collector dosage and the impeller speed) on the recovery and grade of the concentrate obtained by the Jordanian phosphate flotation concentration procedure, was therefore taken into consideration.…”

Section: Type Of Mineral Raw Materialsmentioning

confidence: 99%

Soft computing-based modeling of flotation processes – A review

Jovanović

Miljanović

Jovanović

2015

Minerals Engineering

View full text Add to dashboard Cite

Section: Type Of Mineral Raw Materialsmentioning

confidence: 99%

Soft computing-based modeling of flotation processes – A review

Jovanović

Miljanović

Jovanović

2015

Minerals Engineering

View full text Add to dashboard Cite

“…This may be due to its high efficiency and relatively low cost. It also has some applications in other fields such as paper deinking and wastewater treatment [20][21][22][23][24][25][26][27][28][29] The main principle of froth flotation relies on the differences in physiochemical properties of particles. In flotation, the differences in interfacial tension between phases (liquid, gas, solid) is utilized to selectively separate valuable minerals particles i.e kerogen particles in the case of oil shale.…”

Section: Froth Flotationmentioning

confidence: 99%

Beneficiation of Oil Shale by Froth Flotation: Critical Review

Al-Thyabat¹,

Al-Zoubi²,

Alnawafleh³

et al. 2014

TOMPJ

View full text Add to dashboard Cite

Oil shale beneficiation by froth flotation hasn't received enough attention in the last two decades. The reason was the economics of the process as well as its environmental impact. However, the recent surge in oil price and recent developments in fine grinding technologies may improve the efficiency of oil shale beneficiation by such process. In this work, oil shale concentration by froth flotation technique was critically reviewed. It was found that most of the work was conducted by conventional mechanical flotation using non-ionic collector such as kerosene. Flotation has more pronounced effect on flotation of low grade oil shale; Almost 95% of ash forming minerals were removed to enrich oil shale concentrate by factor of 2-4 with 60-95 % kerogen recovery and approximately 50-300 % increase in oil yield (L/tonne) .Oil shale retorting economics showed that beneficiation reduced the capital cost for pyrolysis and fractionation by 250 % and spent shale disposal by 270%. However, these saving are offset by the cost of beneficiation (grinding, flotation, and dewatering). Therefore, the key for economical oil shale concentration process is the reduction of fine grinding costs.

show abstract

“…In this case, robustness analysis arises from the application of these model-based methods to partially known chemical processes with dynamic uncertainties. It has been shown in the past literature that artificial neural network models have good performance for capturing and dealing with inherent non-linearity, time varying parameters and timedelays [10]- [14]. However, when the delay is time-varying and the adjustment must be made on-line, the controllers are ill-adapted to meet the real-time requirements.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Adaptive Optimal Control for Flotation Processes With Delayed Feedback and Disturbance

Huang

Gui

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Considering the presence of time-delay in actuators and nonvanishing disturbance, a datadriven control technique is developed based on adaptive dynamic programming (ADP) to solve the reagents control problem for flotation processes. First, the reagents control problem is converted into an optimal regulator control problem. Second, a policy iteration (PI) algorithm has been adopted to find desirable adaptive suboptimal controllers. Unlike conventional controllers (PID, MPC) design, the proposed method can achieve the desired control performance by only employing online production data without the complete knowledge of the underlying flotation process dynamics. Specifically, the flotation indexes (tailing grade and concentrate grade) are forced to track the desired values with disturbance rejection and keep reagents consumption to a minimum. The convergence and stability of the proposed data-driven optimal control method are given, and the efficacy is validated in the simulation environment with industrial data. INDEX TERMS Adaptive dynamic programming (ADP), disturbance rejection, flotation processes, inputs time-delay, reagents control.

show abstract

On the optimization of froth flotation by the use of an artificial neural network

Cited by 55 publications

References 14 publications

Soft computing-based modeling of flotation processes – A review

Soft computing-based modeling of flotation processes – A review

Beneficiation of Oil Shale by Froth Flotation: Critical Review

Data-Driven Adaptive Optimal Control for Flotation Processes With Delayed Feedback and Disturbance

Contact Info

Product

Resources

About