Safety control modeling method based on Bayesian network transfer learning for the thickening process of gold hydrometallurgy

doi:10.1016/j.knosys.2019.105297

Knowledge-Based Systems

Volume 192, 15 March 2020, 105297

https://doi.org/10.1016/j.knosys.2019.105297 Get rights and content

Abstract

When the data information of target domain is very limited, it is difficult to establish the accurate model to analyze the target problem. For the safety control modeling problem, this paper develops a new Bayesian network (BN) transfer learning strategy for the thickening process of gold hydrometallurgy. First of all, the safety control modeling problem in this process is analyzed deeply. When the data information of abnormality is insufficient, the safety control modeling problem is transformed into the BN transfer learning problem. Furthermore, the new BN transfer learning strategy is proposed, which includes the structure and parameters transfer learning methods. For the structure transfer learning, by integrating the common structural information of multiple sources and the useful information of target, the final structure of target is determined. For the parameters transfer learning, by distinguishing the similarity of multiple sources, the parameters of target are obtained by the fusion algorithm. Finally, the proposed method is verified by the Asia network and it is applied to establish the safety control model for the thickening process of gold hydrometallurgy. The simulation results demonstrate that the proposed method is effective and owns the better performances than the traditional modeling method.

Introduction

As an important technique of refining gold in the industrial process [1], hydrometallurgy includes the sub-processes of flotation, concentration, leaching, washing and cementation. Before the cyanide leaching, the slurry needs to be concentrated by the thickener and the pressure filter to get the high solid slurry. This process is called as the thickening process which is a key process to guarantee the efficiency of the following cyanide leaching. When the characteristics of raw materials change and the operation strategy is improper, the abnormity will occur. Because of the high economic value of gold, the occurrence of abnormity will lead to the serious financial losses or even safety threat. Therefore, the monitoring and identification of abnormity and making the corresponding safety control scheme attract more and more attention. These researches can ensure that the process runs well. The existing fault detection and safety control methods mainly include the model-based methods [2], [3], [4] and the data-driven methods [5], [6], [7], [8]. However, when there is no accurate mechanism model available in the research field, the model-based method will not obtain good performance. The data-driven methods break up the limitations of model-based methods. Based on the collected data information, the condition can be monitored by the data-driven modeling methods. In these methods, it is assumed that the data information is sufficient to establish the monitoring model and the safety control model. However, for the most data-driven methods, the ability to use the expert knowledge and operation experience is limited.

As an intelligent machine learning method, Bayesian network (BN) provides us a new way to solve the problem, which can fuse the expert knowledge and data information to establish the model effectively. For the safety control problem in the thickening process of gold hydrometallurgy, the paper [9] proposed the safety control scheme based on the BN for two common abnormities. Based on the research results in the paper [9], the paper [10] analyzed the third common abnormity and proposed the updating learning scheme for the established BN model. However, the methods in the papers [9], [10] are all proposed based on the sufficient data information of abnormities. Because the abnormity may cause huge losses and safety threat, few factories would like to make abnormity deliberately and collect the data of abnormity. The collection of corresponding good safety control scheme for every abnormity becomes more difficult. In addition, the occurrence of some abnormities may need to experience a long time. It results in the difficulty of collecting the data information of abnormity further. When the data of abnormity is insufficient, it is difficult to establish the accurate model to solve the target problem.

Under this situation, the transfer learning and domain adaptation inspire us from a new angle to solve the problem. By collecting the useful information of related sources whose abnormality data have been collected and/or the model has been established, the problem of target can be solved by utilizing the related information effectively. Transfer learning has been applied in the various fields and obtains the extensive attention, such as, prediction [11], [12], [13], classification [14], [15], filtering [16], [17] and so on. Therefore, for the safety control modeling problem in the thickening process of gold hydrometallurgy, when the data information of abnormity is insufficient, other thickening processes in the same factory and/or other factories which use the hydrometallurgy technology to produce gold can be considered as the related sources to provide the useful information. When applying the information of related sources, the differences of the relationships of variables and the distributions of parameters between the sources and target need to be focused. Based on the existing research results [9], [10] on the safety control for the thickening process of gold hydrometallurgy, this paper considers that how to establish effective model to solve the safety control problem when the data information of abnormity is insufficient. Because BN is used to model the target problem in the existing research results, the safety control modeling problem is transformed into the BN transfer learning problem.

The transfer learning survey based on the computational intelligence methods has been provided by the paper [18]. The existing transfer learning researches mainly focus on the neural network model [19], [20]. For the BN transfer learning method, the related studies are limited relatively. For the BN structure transfer learning, the paper [21] proposed a new weighted sum of the conditional independence measures by combining measures from the target task with the auxiliary tasks. The papers [22], [23] considered the BN structure transfer learning method for the multitask learning based on the search and score techniques. For the BN parameters transfer learning, the paper [24] proposed the BN parameters transfer learning algorithm based on both network and fragment relatedness. In this process, the problem of heterogeneous relatedness was analyzed and solved. The paper [21] introduced the distance based linear pooling and local linear pooling probability aggregation methods to combine the probability estimates from the target task with those from the auxiliary tasks. However, when measuring the weights of different sources, the proposed method only considered the influences of conditional probability tables (CPTs) entry size and dataset size, and the fitness of source to the target domain was ignored. In addition, the expert knowledge plays the important role in the process of establishing the model of target problem. It is an effective way to improve the accuracy of model by integrating the expert knowledge into transfer learning. The paper [25] transferred the qualitative and quantitative knowledge to monitor the similar batch process. By incorporating the domain knowledge, the paper [26] relaxed the assumption condition when evaluating the task-relatedness in multitask BN structure learning. The paper [27] presented the new probabilistic graphical models parameters transfer learning method by the transferred prior and constraints based on the expert knowledge.

As far as we know, no research results focus on the safety control modeling problem for the thickening process of gold hydrometallurgy when the data information of target is too scarce to establish an accurate model. Therefore, inspired by the expert knowledge and transfer learning, this paper proposes a new safety control modeling method for the thickening process of gold hydrometallurgy based on the BN transfer learning strategy. In this process, the safety control problem is analyzed based on the existing research results. When the data information of target is very limited, the safety control modeling problem is transformed into the BN transfer learning problem. Furthermore, a new BN transfer learning strategy is proposed. By extracting the common structural information (CSI) of multiple sources and integrating the useful information of target, the final structure of target can be obtained. The parameters of target can be learned by fusing the parameters of multiple sources owning the different similarities and target. Finally, some simulation results are shown to verify the effectiveness of proposed method. The proposed transfer learning strategy is applied to establish the safety control model for the thickening process of gold hydrometallurgy when the dosages of flocculants are in the different conditions. The simulation results imply that the proposed approach is effective and owns the better performances than the traditional modeling method which uses the limited data information of target.

The contributions of this paper can be summarized as follows. On the one hand, this paper proposes the new safety control modeling method based on the transfer learning for the thickening process of gold hydrometallurgy. On the other hand, this paper proposes the new BN transfer learning strategy. By integrating the CSI of multiple sources and the useful information of target, the final structure of target is determined. By distinguishing the similarity of multiple sources, the parameters of target are obtained by the fusion algorithm. The proposed method owns the generality, and it can be applied to solve the similar problem in the other research backgrounds.

The remaining sections of this article are organized as follows. Based on the existing research results on the safety control for the thickening process, the problem to solve in this paper is analyzed deeply in Section 2. The new BN transfer learning method is proposed. The structure and parameters transfer learning methods are shown respectively in Section 3. In Section 4, the proposed algorithm is verified by a set of simulation results. Furthermore, the proposed method is applied to establish the safety control model for the thickening process of gold hydrometallurgy. Finally, Section 5 concludes the paper.

Section snippets

The existing safety control research results for the thickening process

The simplified schematic diagram of thickening process can be depicted by Fig. 1.

This process consists of thickener, pressure filter, buffer slots, slurry pumps and valves. For the problems of abnormity identification and safety control in the thickening process of gold hydrometallurgy, the expert knowledge and operation experience have been extracted and summarized, and the data information of relevant variables have been collected by all kinds of sensors. In the existing research results [9],

The proposed BN structure transfer learning strategy

In this section, the new BN structure transfer learning strategy is proposed to obtain the structure of target. It needs to be considered that how to apply the useful information of multiple sources and the limited information of target to learn the structure of target. The specific process can be depicted by Fig. 2.

The proposed BN structure transfer learning method includes three main missions. At first, the CSI of multiple sources needs to be extracted to reflect the common characteristics of

Experimental results

Firstly, to demonstrate the feasibility of proposed method, this section presents the experiments on the well-known Asia network [28], [29], [30], [31]. The network structure of Asia network is shown in Fig. 4. The Asia network is used to represent the relationships for the Chest Clinic, which is a diagnostic demonstrative BN. Then the proposed BN transfer learning strategy is applied to establish the safety control model for the thickening process of gold hydrometallurgy, which is compared

Conclusions

This paper develops a new safety control modeling method based on the BN transfer learning strategy for the thickening process of gold hydrometallurgy. First of all, by analyzing the existing research results on the safety control for the thickening process of gold hydrometallurgy, the problem to solve is transformed into the BN transfer learning problem. Furthermore, a new BN transfer learning strategy is proposed, which includes the structure transfer learning and the parameters transfer

CRediT authorship contribution statement

Hui Li: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Writing - original draft. Fuli Wang: Writing - review & editing, Supervision, Project administration, Funding acquisition. Hongru Li: Writing - review & editing, Supervision, Funding acquisition. Qingkai Wang: Resources.

Acknowledgments

This work was supported by the National Natural Science Foundation of China [grant numbers 61533007, 61873049, 61973057], the Foundation for Innovative Research Groups of the National Natural Science Foundation of China [grant numbers 61621004], the National Key Research and Development Program of China [grant numbers 2017YFB0304205].

References (31)

de Andrade LimaL.R.P.
Nonlinear data reconciliation in gold processing plants
Miner. Eng.
(2006)
LiL. et al.
Performance-based fault detection and fault-tolerant control for automatic control systems
Automatica
(2019)
LiuY. et al.
Reconstruction in integrating fault spaces for fault identification with kernel independent component analysis
Chem. Eng. Res. Des.
(2013)
LiH. et al.
A safe control scheme under the abnormity for the thickening process of gold hydrometallurgy based on Bayesian network
Knowl.-Based Syst.
(2017)
LiH. et al.
The updating strategy for the safe control Bayesian network model under the abnormity in the thickening process of gold hydrometallurgy
Neurocomputing
(2019)
LiuX. et al.
Multimode tool tip dynamics prediction based on transfer learning
Robot. Comput.-Integr. Manuf.
(2019)
AnamA. et al.
Classification of scaled texture patterns with transfer learning
Expert Syst. Appl.
(2019)
TaloM. et al.
Application of deep transfer learning for automated brain abnormality classification using MR images
Cogn. Syst. Res.
(2019)
GrolmanE. et al.
Utilizing transfer learning for in-domain collaborative filtering
Knowl.-Based Syst.
(2016)
LuJ. et al.
Transfer learning using computational intelligence: A survey
Knowl.-Based Syst.
(2015)

SalakenS.M. et al.

Extreme learning machine based transfer learning algorithms: A survey

Neurocomputing

(2017)

ZhouY. et al.

When and where to transfer for bayes net parameter learning

Expert Syst. Appl.

(2016)

KimD.W. et al.

Structure learning of bayesian networks by estimation of distribution algorithms with transpose mutation

J. Appl. Res. Technol.

(2013)

JinY. et al.

An average dwell-time method for fault-tolerant control of switched time-delay systems and its application

IEEE Trans. Ind. Electron.

(2019)

TranH.M. et al.

Distributed functional observer based fault detection for interconnected time-delay systems

IEEE Syst. J.

(2019)

Cited by (12)

A Bayesian network method using transfer learning for solving small data problems in abnormal condition diagnosis of fused magnesia smelting process
2024, Control Engineering Practice
Intelligent abnormal condition diagnosis is key to the safe and stable operation of the fused magnesia smelting process (FMSP). Existing studies have applied the Bayesian network (BN) to the FMSP with sufficient data. However, learning an accurate BN model for a new FMSP using small data isn't easy. Furthermore, the unreasonable diagnosis may seriously affect product quality and security threats. To this end, we present a novel BN transfer learning (BNTL) method to resolve this abnormal condition diagnosis problem using small data. The abnormal condition diagnosis model is established offline based on the proposed BNTL method, and the occurrence or extent of abnormal conditions is identified online based on the diagnosis model and real-time process information. The BNTL involves structure and parameter transfer learning. Among them, structure transfer learning is based on score and search. A new scoring function is proposed to evaluate the local structure of the candidate target domain by weighted integration of source and target domain data based on similarity. The search process is based on the genetic algorithm with other constraints that remove loops and control the number of parent nodes. After learning the structure, parameter transfer learning is done according to a new similarity evaluation and fusion algorithm. The public network is first used to evaluate the BNTL method. Then, it is utilized to build the abnormal condition diagnosis model of the FMSP using small data. Experimental results show that the recognition accuracy is significantly improved compared with other advanced methods in a limited data environment.
Operational adjustment modeling approach based on Bayesian network transfer learning for new flotation process under scarce data
2023, Journal of Process Control
Establishing an intelligent operational adjustment model is significant for optimizing flotation performance and realizing the stable control of the flotation process. When sufficient historical data is available, the Bayesian network (BN) has been used to achieve this goal due to its powerful uncertainty modeling and reasoning capabilities. However, for a new flotation process in the early stage with scarce data, an accurate BN model can hardly be established to make reliable decisions. In this scenario, it is an effective way to transfer data or knowledge from other similar flotation processes to the new flotation process to help complete the target BN modeling task. Therefore, the operational adjustment modeling problem is transformed into the BN transfer learning problem. Moreover, this article proposes a new BN transfer learning approach, including structure and parameters transfer learning techniques. For structure transfer learning, a majority voting mechanism is proposed to get an integrated result of conditional independence tests and generates the network structure based on them. For parameters transfer learning, the sources are judged whether to be used to learn the parameters first, and then the suitable sources are used to learn the network parameters based on the weight determined by the similarity. The Asia network first assesses the proposed approach and then applies it to real-world flotation operational adjustment decisions. Experimental results on the Asia network show that the proposed approach can learn more accurate structure and parameters according to F1 score, Hamming distance, and KL divergence indicators compared to existing advanced methods. Furthermore, the experimental results of the flotation process show that the inference accuracy is improved from 57.1% to 85.7% compared with the traditional modeling method.
Efficient gold recovery from waste electronic and electric equipment by amino-modified covalent triazine frameworks
2023, Chemical Engineering Journal
Recycling gold from e-waste is not only conducive to alleviating the pressure on resources and environment, but also has high economic value. Therefore, construction of adsorbents with high capacity and selectivity and low cost is significative for gold recovery from waste electronic and electric equipment (WEEE). Herein, amino-functionalized covalent triazine frameworks (NH₂-CTFs) were synthesized by ionothermal conditions. NH₂-CTF-1 and NH₂-CTF-2 with high porosity and good thermal stability exhibit excellent gold recovery performance. Meanwhile, gold ions can be in situ reduced into gold nanoparticles by NH₂-CTFs along with the adsorption process. Furthermore, NH₂-CTF-1 and NH₂-CTF-2 present good gold adsorption selectivity from WEEE. Notably, NH₂-CTF-1 possesses high gold adsorption capacity (909 mg g⁻¹) and outstanding recovery profit. These excellent performances confirm the potential of NH₂-CTF-1 and NH₂-CTF-2 for gold recovery from WEEE.
Construction of porphyrin and viologen-linked cationic porous organic polymer for efficient and selective gold recovery
2022, Journal of Hazardous Materials
Citation Excerpt :
However, selectively recycling gold still remains a challenge because of the interference of various metal ions and its very low content in secondary resources. Many gold recovery technologies have been reported, including hydrometallurgy (Li et al., 2020), pyrometallurgy (Liu et al., 2009), adsorption (F. Liu et al., 2019; Z. Liu et al., 2019), solvent extraction (Doidge et al., 2019; Kubota et al., 2019; Raiguel et al., 2020) and ion exchange (Choi et al., 2020; Murakami et al., 2015; Xing and Lee, 2019). However, most of these techniques are beset by their defects, such as consumption of organic solvents, high-cost, incomplete metal removal, decreased efficiency, labor-intensity and harm to the environment (Kim et al., 2018).
Recycling precious metals from electronic waste not only benefits environmental protection, but is also favorable for alleviating resource shortages. Ionic porous organic polymers, as one type of burgeoning material, are regarded as excellent adsorbents due to their high ion density, but their application in precious metal recovery is still very limited. Here, V-PPOP-Br, a highly stable and easy-to-build cationic porous organic polymer, was successfully prepared for the first time. By linking porphyrins with viologens, V-PPOP-Br obtained the characteristics of a hierarchical porous structure, a high ion density skeleton, and a rich nitrogen content, which gave it an ultrahigh adsorption capacity (Q_max = 792.22 mg g⁻¹) and rapid adsorption rate for Au(III). V-PPOP-Br also had an effective Au(III) recovery capability from SIM cards. Mechanism investigation confirmed that this remarkable adsorption performance was attributed to the interplay of ion exchange, redox reactions and coordination. Moreover, V-PPOP-Br had excellent recyclability and could maintain an ultrahigh adsorption efficiency of 81% after eight consecutive adsorption-desorption experiments. These excellent performances as well as the roughly calculated gold recycling economics ($37.37/g V-PPOP-Br) confirmed that it possesses promising potential as an ionic porous material for gold recovery.
Fully probabilistic design for knowledge fusion between Bayesian filters under uniform disturbances
2022, Knowledge-Based Systems
Citation Excerpt :
Bayesian transfer learning (BTL)—to be championed in this paper—usually adopts a complete stochastic modelling framework for source–target interaction. Approaches include Bayesian networks [12], Bayesian neural networks [13] and hierarchical Bayesian approaches [14]. In contrast, in [15], BTL is defined as the conditioning of a target probability distribution on a transferred source distribution.
This paper considers the problem of Bayesian transfer learning-based knowledge fusion between linear state–space processes driven by uniform state and observation noise processes. The target task conditions on probabilistic state predictor(s) supplied by the source filtering task(s) to improve its own state estimate. A joint model of the target and source(s) is not required and is not elicited. The resulting decision-making problem for choosing the optimal conditional target filtering distribution under incomplete modelling is solved via fully probabilistic design (FPD), i.e. via appropriate minimization of Kullback–Leibler divergence (KLD). The resulting FPD-optimal target learner is robust, in the sense that it can reject poor-quality source knowledge. In addition, the fact that this Bayesian transfer learning (BTL) scheme does not depend on a model of interaction between the source and target tasks ensures robustness to the misspecification of such a model. The latter is a problem that affects conventional transfer learning methods. The properties of the proposed BTL scheme are demonstrated via extensive simulations, and in comparison with two contemporary alternatives.
Nonlinear soft sensor development for industrial thickeners using domain transfer functional-link neural network
2021, Control Engineering Practice
The thickener is used to provide slurries with a stable and satisfactory concentration in the ore dressing plant. To efficiently control an industrial thickener, a soft sensor model should be built first to predict the underflow concentration. In industrial sites, it is usually expensive and time-consuming to collect sufficient high-quality data to develop a data-driven model. In this work, a nonlinear regression method for transfer learning is proposed to solve this problem, which is named domain transfer functional-link neural network (DT-FLNN). The framework of the proposed method includes two stages, and the issue of domain adaption is separately considered at each stage. In the first stage, the activation matrix of the source domain is reconstructed to narrow the distribution difference, and the augmented input matrices of the source and target domains are formulated. Then, the latent variable (LV) based linear regression method for transfer learning is performed at the second stage to train the FLNN of the target domain, and the task of domain adaption is realized by introducing a regularization term. Besides, a systematic method is also presented to determine the hyper-parameters in the proposed DT-FLNN method. The efficiency of the proposed method is evaluated by employing a numerical example and an industrial application. Compared with other nonlinear regression approaches for transfer learning, the proposed method can further increase the prediction accuracy and reduce the influence of noise.

View all citing articles on Scopus

^☆: No author associated with this paper has disclosed any potential or pertinent conflicts which may be perceived to have impending conflict with this work. For full disclosure statements refer to https://doi.org/10.1016/j.knosys.2019.105297.

¹: Correspondence to: P.O. Box 135, No. 11 St.3 Wenhua Road, Heping District Shenyang, Liaoning Province, 110819, China.

View full text

Safety control modeling method based on Bayesian network transfer learning for the thickening process of gold hydrometallurgy☆

Abstract

Introduction

Section snippets

The existing safety control research results for the thickening process

The proposed BN structure transfer learning strategy

Experimental results

Conclusions

CRediT authorship contribution statement

Acknowledgments

Miner. Eng.

Automatica

Chem. Eng. Res. Des.

Knowl.-Based Syst.

Neurocomputing

Robot. Comput.-Integr. Manuf.

Expert Syst. Appl.

Cogn. Syst. Res.

Knowl.-Based Syst.

Knowl.-Based Syst.

Neurocomputing

Expert Syst. Appl.

J. Appl. Res. Technol.

An average dwell-time method for fault-tolerant control of switched time-delay systems and its application

IEEE Trans. Ind. Electron.

Distributed functional observer based fault detection for interconnected time-delay systems

IEEE Syst. J.