Knowledge-Based Global Operation of Mineral Processing Under Uncertainty

Ding, Jinliang; Chai, Tianyou; Wang, Hong; Chen, Xinkai

doi:10.1109/tii.2012.2205394

Cited by 42 publications

(10 citation statements)

References 27 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model that predicts the production indices uses a method that combines the least-squares support vector machine with probability density function (PDF) control theory-based parameter selection (Ding, Chai, and Wang 2011). The PriPIDT and PostPIDT employ a rough setbased rule-mining approach (Pawlak 1982;Ding et al 2012). …”

Section: System Design and Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

An intelligent factory-wide optimal operation system for continuous production process

Ding

Chai

Wang

et al. 2015

Enterprise Information Systems

Self Cite

View full text Add to dashboard Cite

In this study, a novel intelligent factory-wide operation system for a continuous production process is designed to optimise the entire production process, which consists of multiple units; furthermore, this system is developed using process operational data to avoid the complexity of mathematical modelling of the continuous production process. The data-driven approach aims to specify the structure of the optimal operation system; in particular, the operational data of the process are used to formulate each part of the system. In this context, the domain knowledge of process engineers is utilised, and a closed-loop dynamic optimisation strategy, which combines feedback, performance prediction, feedforward, and dynamic tuning schemes into a framework, is employed. The effectiveness of the proposed system has been verified using industrial experimental results. ARTICLE HISTORY

show abstract

Section: System Design and Algorithmmentioning

confidence: 99%

“…Here, the incremental association rules are mined from the actual operation data of an industrial process using the rough sets and the association rule-mining methods. The details of the above algorithm can be found in Ding et al (2009Ding et al ( , 2012.…”

Section: A Priori Evaluation and A Posteriori Evaluation Of Productiomentioning

confidence: 99%

An intelligent factory-wide optimal operation system for continuous production process

Ding

Chai

Wang

et al. 2015

Enterprise Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, more than one production index in the beneficiation process need to be optimized in consideration of such factors as market requirement and economic benefits [13]. The optimal solutions of these production indices usually cannot be obtained simultaneously, thus making OIOB a typical multi-objective optimization problem (MOP).…”

Section: Introductionmentioning

confidence: 99%

Multitasking Multiobjective Evolutionary Operational Indices Optimization of Beneficiation Processes

Yang

Ding

Jin

et al. 2019

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

Abstract-Operational indices optimization is crucial for the global optimization in beneficiation processes. This paper presents a multi-tasking multi-objective evolutionary method to solve operational indices optimization, which involves a formulated multi-objective multifactorial operational indices optimization problem (MO-MFO) and a proposed multi-objective multifactorial optimization algorithm for solving the established MO-MFO problem. The MO-MFO problem includes multiple level of accurate models of operational indices optimization, which are generated on the basis of a dataset collected from production. Among the formulated models, the most accurate one is considered to be the original functions of the solved problem, while the remained models are the helper tasks to accelerate the optimization of the most accurate model. For the multifactorial optimization algorithm, the assistant models are alternatively in multi-tasking environment with the accurate model to transfer their knowledge to the accurate model during optimization in order to enhance the convergence of the accurate model. Meanwhile, the recently proposed two-stage assortative mating strategy for a multi-objective multifactorial optimization algorithm is applied to transfer knowledge among multi-tasking tasks. The proposed multi-tasking framework for operational indices optimization has conducted on 10 different production Conditions of beneficiation. Simulation results demonstrate its effectiveness in addressing the operational indices optimization of beneficiation problem.Note to Practitioners−Operational indices optimization is a typical method to achieve global production optimization by efficiently coordinating all the indices to improve the production indices. In this paper, a multi-objective multi-tasking framework is developed to address the operational indices optimization, which includes a multi-taking multi-objective operational indices optimization problem formulation and a multi-taking multiobjective evolutionary optimization to solve the above formulated optimization problem. The proposed approach can achieve a solution set for the decision making. The simulation results on a real beneficiation process in China with 10 operational conditions show that the proposed approach is able to obtain a superior solution set, which is associate with a higher grade and yield of the product.

show abstract

“…For monitoring diversified processes, a variety of knowledgeable strategies have been presented [4,[21][22][23] including subPLS modeling algorithm [24][25][26], recursive or adaptive PCA [27], model library based method [28], localized discriminant analysis [29], multiblock PLS, discriminant analysis [26], gaussian mixture model [30], and diversified statistical analysis method [20,31,32]. Among the existing nonlinear methods, kernel-based techniques have been successfully developed for tackling the nonlinear problem in recent years [33,34].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Diversified Processes Monitoring

Fan

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The paper proposed a new method to classify and establish the monitoring model for diversified processes data with multiscale. The advantages of the proposed approach are listed as follows. (1) The issues of diversified processes data with multiscale are considered and the fault monitoring effect is enhanced. (2) From a new perspective, the common and specific characteristic subspaces are extracted to help simplify the structure of the monitoring model. (3) It makes the correlation between the common subspace itself and input-output dataset of each mode as close as possible. The effect of the proposed method has been shown in the Experiment Results section.

show abstract

Knowledge-Based Global Operation of Mineral Processing Under Uncertainty

Cited by 42 publications

References 27 publications

An intelligent factory-wide optimal operation system for continuous production process

An intelligent factory-wide optimal operation system for continuous production process

Multitasking Multiobjective Evolutionary Operational Indices Optimization of Beneficiation Processes

Nonlinear Diversified Processes Monitoring

Contact Info

Product

Resources

About