Constrained dynamic multi-objective evolutionary optimization for operational indices of beneficiation process

Yang, Cuie; Ding, Jinliang

doi:10.1007/s10845-017-1319-1

“…This approach employs specific non-linear models using polynomials up to an order of two and restricts the synchronous optimization to at most two quality targets (responses), thus to two objectives (achieved by the reformulation of the problem with an additional constraint on the second objective). Similar considerations (two objectives restriction) go to the approach in [58], which employs RBF neural networks as surrogate models, but no explicit DoE is described there. The approach in [21] performs a plain orthogonal experimental design to generate an initial data set for model training and achieves single-objective (i.e., lens thickness) process optimization through reinforcement learning techniques, which require permanent user/operator feedback during the on-line process (which is not available/applicable in our use case).…”

Section: Comparison With Related Workmentioning

confidence: 99%

A soft-computing framework for automated optimization of multiple product quality criteria with application to micro-fluidic chip production

Zăvoianu

¹

,

Lughofer

²

,

Pollak

³

et al. 2021

Applied Soft Computing

5

0

View full text Add to dashboard Cite

We describe a general strategy for optimizing the quality of products of industrial batch processes that comprise multiple production stages. We focus on the particularities of applying this strategy in the field of micro-fluidic chip production. Our approach is based on three interacting components: (i) a new hybrid design of experiments (DoE) strategy that combines expert-and distribution-based space exploration with model-based uncertainty criteria to obtain a representative set of initial samples (i.e., settings of essential machining process parameters), (ii) construction of linear and non-linear predictive mappings from these samples to describe the relation between machining process parameters and resulting quality control (QC) values and (iii) incorporation of these mappings as surrogate fitness estimators into a multi-objective optimization process to discover settings that outperform those routinely used by operators. These optimized settings lead to final products with better quality and/or higher functionality for the clients. The optimization module employs a co-evolutionary strategy we developed that is able to deliver better Pareto non-dominated solutions than the renowned NSGA-II multi-objective solver. We applied our proposed highlevel surrogate-based multi-objective strategy both in a single/late-stage optimization scenario and in a more challenging multi-stage scenario, yielding final optimization results that improved parameter settings and thus product quality compared to standard expert-based production process parameterizations.

show abstract

“…In recent years, researchers have studied the optimization of the production process of metal mines in terms of three major aspects. The first is the optimization of metal mine production in the beneficiation process [7][8][9][10][11]. Obviously, the local optimization of a unit process does not guarantee the global optimization of the process.…”

Section: Introductionmentioning

confidence: 99%

Production Process Optimization of Metal Mines Considering Economic Benefit and Resource Efficiency Using an NSGA-II Model

Xun-hong¹,

Gu²,

Liu³

et al. 2018

Preprint

View full text Add to dashboard Cite

The optimization of the production process of metal mines has been traditionally driven only by economic benefits while ignoring resource efficiency. However, it has become increasingly aware of the importance of resource efficiency since mineral resource reserves continue to decrease while the demand continues to grow. To better utilize the mineral resources for sustainable development, this paper proposes a multi-objective optimization model of the production process of metal mines considering both economic benefits and resource efficiency. Specifically, the goals of the proposed model are to maximize the profit and resource utilization rate. Then, the fast and elitist Non-Dominated Sorting Genetic Algorithm (NSGA-II) is used to optimize the multi-objective optimization model. The proposed model has been applied to the optimization of the production process of a stage in the Huogeqi Copper Mine. The optimization results provide a set of Pareto-optimal solutions that can meet varying needs of decision makers. Moreover, compared with those of the current production indicators, the profit and resource utilization rate of some points in the optimization results can increase respectively by 2.99% and 2.64%. Additionally, the effects of the decision variables (geological cut-off grade, minimum industrial grade and loss ratio) on objective functions (profit and resource utilization rate) were discussed using variance analysis. The sensitivities of the Pareto-optimal solutions to the unit copper concentrate price were studied. The results show that the Pareto-optimal solutions at higher profits (with lower resource utilization rates) are more sensitive to the unit copper concentrate prices than those obtained in regions with lower profits.

show abstract

“…The optimization of the metal mines production process is an effective way to raise the economic benefits of enterprises and contribute to the sustainable development of resources.In recent years, researchers have studied the optimization of the production process of metal mines in terms of three major aspects. The first is the optimization of metal mine production in the beneficiation process [7][8][9][10][11]. Obviously, the local optimization of a unit process does not guarantee the global optimization of the process.…”

mentioning

confidence: 99%

Production Process Optimization of Metal Mines Considering Economic Benefit and Resource Efficiency Using an NSGA-II Model

Xun-hong

¹

,

Gu

²

,

Liu

³

et al. 2018

View full text Add to dashboard Cite

The optimization of the production process of metal mines has been traditionally driven only by economic benefits while ignoring resource efficiency. However, it has become increasingly aware of the importance of resource efficiency since mineral resource reserves continue to decrease while the demand continues to grow. To better utilize the mineral resources for sustainable development, this paper proposes a multi-objective optimization model of the production process of metal mines considering both economic benefits and resource efficiency. Specifically, the goals of the proposed model are to maximize the profit and resource utilization rate. Then, the fast and elitist Non-Dominated Sorting Genetic Algorithm (NSGA-II) is used to optimize the multi-objective optimization model. The proposed model has been applied to the optimization of the production process of a stage in the Huogeqi Copper Mine. The optimization results provide a set of Pareto-optimal solutions that can meet varying needs of decision makers. Moreover, compared with those of the current production indicators, the profit and resource utilization rate of some points in the optimization results can increase respectively by 2.99% and 2.64%. Additionally, the effects of the decision variables (geological cut-off grade, minimum industrial grade and loss ratio) on objective functions (profit and resource utilization rate) were discussed using variance analysis. The sensitivities of the Pareto-optimal solutions to the unit copper concentrate price were studied. The results show that the Pareto-optimal solutions at higher profits (with lower resource utilization rates) are more sensitive to the unit copper concentrate prices than those obtained in regions with lower profits.Processes 2018, 6, 228 2 of 22 realistic problem to optimize the production process of metal mines for mining mineral resources with the greatest economic benefits and resource efficiency to better utilize the mineral resources for sustainable development [2].The production process of metal mines is a complex industrial process, consisting of three unit processes in series, i.e., the exploration process, the mining process and the beneficiation process. The input of the latter unit process is the output of the previous one [3,4]. The optimization of the production process of metal mines is to determine the best production technology indicators that have a significant impact on economic benefits and resource efficiency [5,6]. Technical production indicators include the recoverable reserves, average ore grade, geological cut-off grade, minimum industrial grade, loss ratio, dilution ratio, raw ore grade and volume, concentrate grade and volume, and concentration ratio. As the market changes and production technology advances, it is necessary to adjust and optimize these indicators in time to achieve the best results. The optimization of the metal mines production process is an effective way to raise the economic benefits of enterprises and contribute to the sustainable development of res...

show abstract

Constrained dynamic multi-objective evolutionary optimization for operational indices of beneficiation process

Cited by 23 publications

References 30 publications

A soft-computing framework for automated optimization of multiple product quality criteria with application to micro-fluidic chip production

A soft-computing framework for automated optimization of multiple product quality criteria with application to micro-fluidic chip production

Production Process Optimization of Metal Mines Considering Economic Benefit and Resource Efficiency Using an NSGA-II Model

Production Process Optimization of Metal Mines Considering Economic Benefit and Resource Efficiency Using an NSGA-II Model

Contact Info

Product

Resources

About