=Paper=
{{Paper
|id=Vol-3816/paper75
|storemode=property
|title=Developing Deep Learning Based Intelligent Perception Algorithm for Thickener Equipment Monitoring
|pdfUrl=https://ceur-ws.org/Vol-3816/paper75.pdf
|volume=Vol-3816
|authors=Zuochen Liu,Qingkai Wang,Jiandong Dang,Xiaochun Wang,Kang Li,Roberto Avogadro,Dumitru Roman,Xiang Ma
|dblpUrl=https://dblp.org/rec/conf/rulemlrr/LiuWDWLARM24
}}
==Developing Deep Learning Based Intelligent Perception Algorithm for Thickener Equipment Monitoring==
https://ceur-ws.org/Vol-3816/paper75.pdf
Developing Deep Learning Based Intelligent Perception
Algorithm for Thickener Equipment Monitoring
Zuochen Liu1,2,†, Qingkai Wang1,2,†, Jiandong Dang3,†, Xiaochun Wang3,†, Kang Li1,2,∗,†,
Roberto Avogadro4,†, Dumitru Roman4,† and Xiang Ma4,∗,†
1 State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process, Beijing 100160, China
2 Beijing General Research Institute of Mining and Metallurgy (BGRIMM), Beijing 100160, China
3 Anhui Tongguan (Lujiang) Mining Co., Ltd, Hefei 231500, Aahui, China
4 SINTEF AS, POB 124, Blindern, 0314 Oslo, Norway
Abstract
Dense dehydration by use of thickener equipment is a critical process in mineral processing, directly
impacting the quality of concentrate products. However, current industrial practices lack effective
methods for monitoring the condition of thickeners. This makes it difficult for operators to accurately
perceive the internal state of the thickener, leading to a relatively inefficient production process. This
paper addresses the challenge of real-time detection of one of the key process parameters, feed rate, in
thickener by employing a data-driven model-ling approach with intelligent perception. The upstream
processes are analyzed, and relevant variables are selected for modeling. The Long Short-Term
Memory (LSTM) - Recurrent Neural Network (RNN) and the Gated Recurrent Unit (GRU) - RNN with
the Particle Swarm Optimization (PSO) algorithm are used to build and train the models. The results
show that the PSO-GRU-based intelligent perception model for thickener feed rate estimation achieves
higher accuracy and shorter training times compared with the LSTM-RNN model.
Keywords
intelligent perception, deep learning, LSTM-RNN, GRU-PSO, thickener 1
1. Introduction
Mineral processing is a crucial and indispensable step after geological exploration and mining,
and before metallurgical or chemical processing in many material production value chains. It
involves converting raw, complex mineral resources into standardized, orderly concentrates
that meet specifications for further processing in smelters or chemical plants [1]. The mined ore
is sequentially subjected to primary crushing, vibrating screening, fine crushing, grinding,
flotation and final thickening, as shown in Figure 1. Moisture content is a critical quality indicator
for concentrated products, making thickening and dewatering a crucial step in the mineral
processing workflow. The thickening process plays an essential role in achieving solid-liquid
separation, with the thickener being the key piece of equipment in this operation [2].
In actual production, the operation of thickening and filtration relies heavily on assessing the
operating conditions of the thickener, with the feed rate being a critical factor. The feed rate is a
nonlinear, dynamic variable, and industrial operations often depend on manual experience,
which can be subjective and imprecise. This makes it difficult for operators to accurately
perceive the internal state of the thickener, leading to a relatively inefficient production process.
RuleML+RR'24: Companion Proceedings of the 8th International Joint Conference on Rules and Reasoning, September 16‐
‐22, 2024, Bucharest, Romania
∗ Corresponding author
† These authors contributed equally.
likang@bgrimm.com (K. Li); xiang.ma@sintef.no (X. Ma)
0000-0003-1867-3919 (K. Li); 0000-0001-6465-0254 (X. Ma)
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
Issues such as low filtration efficiency and high energy consumption consequently arise.
Therefore, optimizing thickener control requires accurate detection of the feed rate. In practice,
ore feed rate detection typically relies on offline sampling or the installation of online analysis
devices. However, due to the limitations of industrial environments, current detection methods
fail to meet the requirements for real-time and accurate measurement [3].
Figure 1. Schematic diagram of conventional beneficiation process and equipment.
With the development of soft sensing technology, data-driven regression models have been
widely used to measure variables that are difficult to obtain directly in real-time. Moreover,
recent years have seen breakthrough advancements in new intelligent sensing technologies,
particularly in deep learning. Dynamic neural networks, represented by Recurrent Neural
Networks (RNN), excel at capturing the temporal dynamics in sequential data. However,
standard RNNs face issues like vanishing and exploding gradients when modeling long-time
series, due to their indiscriminate memory of past data. To tackle this issue, Long Short-Term
Memory (LSTM) networks were designed to selectively forget past information by incorporating
gating units [4]. While LSTM offers superior performance, it comes with increased complexity
and numerous parameters. The Gated Recurrent Unit (GRU) was thus introduced to simplify the
LSTM structure while retaining its powerful performance [5].
In this study, the upstream processes of thickening are analyzed, and relevant data is used to
implement intelligent perception of thickener feed rate using LSTM and GRU based models. The
simulation results, along with actual data, verify that deep learning methods can effectively solve
the problem of online detection of thickener feed rate.
2. Constructing and processing of datasets
The mineral processing workflow is a continuous process that includes crushing, grinding,
flotation, and thickening/filtration, with each step closely interconnected. The output of one
stage typically serves as the input for the next, forming a tightly integrated process chain. From
prior knowledge, it is understood that the feed rate of the thickener is closely related to the
grinding and flotation processes. Given the complexity of these processes which involve
numerous pieces of equipment and sensors, this study selects 58 auxiliary variables from the
grinding and flotation stages that have a strong correlation with the thickener feed rate.
The auxiliary variables' data can be detected in real-time at the industrial site and stored in a
database. The raw data consists of actual operational data from the plant, with a sampling
interval of 5 seconds, resulting in a total of 200,000 data sets. The selected time period for these
samples effectively captures a wide range of conditions during normal process operation.
The raw data, directly sourced from on-site industrial detection equipment, inevitably
contains missing values and random errors. Using such unprocessed data for model building can
significantly reduce predictive accuracy. Therefore, data preprocessing is essential and involves
the following steps:
(1) Handling missing values
Given the 5-second sampling interval, there are instances where equipment or sensor data
change during sampling, leading to unsuccessful data capture. To address this, missing values in
the raw data are identified and filled using forward filling, where the missing data point is
replaced with the value from the preceding timestamp.
(2) Outlier detection
This study employs a moving median method to detect and eliminate outliers. Specifically, a
moving window of length 70 is applied sequentially across the dataset. Within each window, any
data point that deviates from the local median by more than five times the local standard
deviation is classified as an outlier.
(3) Standardization and inverse standardization
The auxiliary variables exhibit significant differences in their values and distributions,
rendering them unsuitable for direct input into the model. To mitigate the effects of differing
dimensions among input variables, the data are standardized to have a mean of 0 and a standard
deviation of 1. This standardized data serves as the input for model training. Consequently, the
model's output, which is based on the standardized input, must undergo inverse standardization
to revert to the original scale. The equations for standardization and inverse standardization are
as follows:
𝑋 (1)
𝑥 𝑋 𝑥 –𝑥 𝑥 (2)
where 𝑥 : the i‐th denormalized data, 𝑋 : the normalized data, 𝑥 and 𝑥 : the minimum
and maximum values of the sample set with N number of data, respectively.
(4) Evaluation criteria
The root mean square error (RMSE) is selected to evaluate the difference between the
observed value 𝑦 and the true value 𝑝𝑟𝑒𝑑 of the model, and the calculated mean relative error
(MRE) is selected to measure the overall deviation between the observed value and the true
value to evaluate the quality of the model, as defined by:
∑
𝑅𝑀𝑆𝐸 (3)
∑ | |
𝑀𝑅𝐸 (4)
3. Intelligent perception models for thickener feed rate prediction
Intelligent perception models are developed for thickener feed rate evaluation using traditional
deep learning-based LSTM-RNN and GRU-RNN. A subset of 10,000 data samples is selected from
the dataset, and models are built using both this subset and the full dataset of 200,000 samples.
The dataset contains 58 input variables, with the thickener feed rate as the output variable. The
data is divided into training, validation, and test sets with a ratio of 0.7:0.15:0.15.
The simulation software Matlab© R2023b is used to build and run the models in a 64-bit
Windows 11 stationary PC with an Intel(R) Core(TM) i9-12900H CPU and a 16.00 GB RAM.
3.1. Intelligent perception model based on LSTM‐RNN
LSTM-RNN is a special recurrent neural network, composed of input gates, for-getting gates, and
output gates which can process and memorize long-term series data. It can effectively alleviate
the problems of gradient vanishing and gradient explosion in ordinary RNNs, and is suitable for
solving the regression and prediction problems of long-term series. Figure 2 shows the process
of building the intelligent perception model based on LSTM. The hyperparameters are selected
for random search optimization, and the Adam optimizer is used for training.
FC
LSTM LSTM . . . LSTM
. . .
Figure 2. Structural diagram of the intelligent perception model based on LSTM.
The RMSE and the MRE for the predicted feed rate in ton/hour (t/h) using the test set
containing 10,000 samples are 0.210 and 4.1%, respectively, and are 0.307 and 5.2% for the full
dataset, respectively, as shown in Figure 3. However, the LSTM model's complexity, longer
training time, higher hardware requirements, and increased number of parameters make the
training process more challenging, which poses difficulties for its application in industrial
settings. To address these issues, the use of a GRU network will be explored.
11.5 15
Actual Actual
11 Predicted Predicted
10.5
10
9.5 10
9
8.5
8
7.5 5
0 500 1000 1500 0 0.5 1 1.5 2 2.5 3
Sampling index Sampling index 104
(a) 10,000 samples out of the full dataset (b) Full dataset
Figure 3. LSTM-RNN predicted feed rate output (t/h), compared with the actual vaules.
3.2. Intelligent perception model based on improved GRU
The GRU model is a further improved structural model of the LSTM, merging the input and
forgetting gates of the LSTM and using only two gating units: the update gate and the reset gate.
At the same time, the particle swarm (PSO) algorithm is used for hyperparameter optimization,
which is an optimization algorithm based on swarm intelligence and finds the optimal solution
through information sharing between individuals [6]. The structure of the GRU-based intelligent
perception model is similar to that of the LSTM model in which the LSTM network is replaced by
the GRU network, and the PSO algorithm is used to optimize the hyperparameters of the GRU.
As shown in Figure 4, the RMSE and the MRE for the predicted feed rate by PSO-GRU using the
test set containing 10,000 samples are 0.153 and 3.5%, respectively, and are 0.136 and 3.4% for
the full dataset, respectively. Actual result comparison shows that the performance of the PSO-
GRU network can well meet the measurement accuracy requirements in the production line for
the sample dataset of 10,000 sets, and the complete dataset with 200,000 sets. Additionally, the
training time for the PSO-GRU model is 35min and 31s, shortened by 19% compared with of the
LSTM model of 43min and 50s.
11.5 18
Actual Actual
11 Predicted 16 Predicted
10.5
14
10
9.5 12
9
10
8.5
8
8
7.5 6
7 4
0 500 1000 1500 0 0.5 1 1.5 2 2.5 3
Sampling index Sampling index 4
10
(a) 10,000 samples out of the full dataset (b) Full dataset
Figure 4. PSO-GRU predicted feed rate output (t/h), compared with the actual values.
4. Conclusions
The feed rate of the thickener is a crucial parameter in its operation. This study proposes several
intelligent perception models to accurately predict the thickener feed rate, utilizing relevant
variables from the grinding and flotation processes to address the challenge of online detection.
Two intelligent perception models are developed based on LSTM and GRU-RNN. The best
performed GRU-RNN model and its advantages over LSTM network are analyzed. This deep
learning-based approach could be applied to actual production, providing a foundation for the
optimized control of the thickener.
Acknowledgements
This work was supported partially by the National Key R&D Program of China (Grant No.
2021YFC2902703)，the Open Foundation of State Key Laboratory of Process Automation in
Mining & Metallurgy/Beijing Key Laboratory of Process Automation in Mining & Metallurgy,
China (Grant No. BGRIMM-KZSKL-2022-4, Grant No. BGRIMM-KZSKL-2023-10), Horizon Europe
funded enRichMyData (Grant No. 101070284), and the bilaterial project "BigDataMine" jointly
funded by National Key R&D Program of China (Grant No. 2019YFE0105000) and the Research
Council of Norway (Grant No. 309691).
References
[1] Hodouin D., Jämsä-Jounela S.-L, Carvalho M.T., Bergh L., “State of the art and challenges in
mineral processing control”. Control Engineering Practice 9.9 (2001): 995-1005.
[2] Shmueli G., Sarstedt M., Hair J. F., Cheah, J. H., Ting, H., Vaithilingam, S., Ringle, C. M.,
“Predictive model assessment in PLS-SEM: guidelines for using PLSpredict”. European
Journal of Marketing 53.11 (2019): 2322–2347.
[3] Chen, H., Huang, W., Huang, J., Cao, C., Yang, L., He, Y., Zeng, L., “Multi-fault condition
monitoring of slurry pump with principle component analysis and sequential hypothesis
test”. International Journal of Pattern Recognition and Artificial Intelligence 34.7 (2020):
2059019.
[4] Graziani, S., Xibilia, M. G., “Design of a soft sensor for an industrial plant with unknown delay
by using deep learning”. in: Proceedings of the 2019 IEEE International Instrumentation and
Measurement Technology Conference, IEEE, Auckland, 2019, pp. 1–6.
[5] Chung, J., Gulcehre, C., Cho, K. H., Bengio, Y., “Empirical evaluation of gated recurrent neural
networks on sequence modeling". arXiv preprint arXiv: 1412.3555, 1–9 (2014).
[6] Kennedy, J., Eberhart, R., “Particle swarm optimization”. in: Proceedings of the International
Conference on Neural Networks, IEEE, Perth, 1995, pp. 1942–1948.