Operating Performance Assessment of Flotation Process Based on Multi-source Heterogeneous Information

doi:10.12068/j.issn.1005-3026.2024.09.001

Abstract

Abstract:

In view of the coexistence of image information and process data information in flotation process and small differences among features of different operation state， a novel operating performance assessment method based on multi?source heterogeneous information and deep learning was proposed for flotation process. Firstly， a residual network （ResNet） is established to extract deep features with more discrimination from original images of different performance grades. Secondly， a stacked sparse performance?relevant autoencoders （SSPAE） model is proposed， which introduces the state level label into the model training to overcome the problem that the traditional autoencoder ignores the state?related characteristics. Furthermore， an image and data feature fusion model based on attention mechanism （AM） is established， and then the fused features are used as the inputs of the SoftMax classifier to train the operating performance assessment model， realizing the reasonable and effective utilization of the multi?source heterogeneous information. Finally， the flotation process data is used for simulation verification. The simulation results show that the proposed method is superior to other comparative methods， verifying its superiority in evaluating the operating performance of flotation processes.

Key words: operating performance assessment, multi?source heterogeneous information, deep learning, attention mechanism, flotation process

CLC Number:

TP 13

Yan LIU, Qi-jie BU, Hong-chen ZHAO, Xin GUO. Operating Performance Assessment of Flotation Process Based on Multi-source Heterogeneous Information[J]. Journal of Northeastern University(Natural Science), 2024, 45(9): 1217-1226.

Figures/Tables 13

References 20

1	Liu Y， Chang Y Q， Wang F L.Online process operating performance assessment and nonoptimal cause identification for industrial processes［J］.Journal of Process Control，2014，24（10）：1548-1555.
2	Chu F， Dai W， Shen J，et al.Online complex nonlinear industrial process operating optimality assessment using modified robust total kernel partial M‑regression［J］.Chinese Journal of Chemical Engineering，2018，26（4）：775-785.
3	Ye L B， Liu Y M， Fei Z S，et al.Online probabilistic assessment of operating performance based on safety and optimality indices for multimode industrial processes［J］.Industrial & Engineering Chemistry Research，2009，48（24）：10912-10923.
4	Zou X Y， Chang Y Q， Wang F L，et al.Process operating performance optimality assessment with coexistence of quantitative and qualitative information［J］.The Canadian Journal of Chemical Engineering，2018，96（1）：179-188.
5	Yan H， Wang F L， Yan G G，et al.Hybrid approach integrating case‑based reasoning and Bayesian network for operational adjustment in industrial flotation process［J］.Journal of Process Control，2021，103：34-47.
6	Li J N， Chai T Y， Lewis F L，et al.Off‑policy Q‑learning：set‑point design for optimizing dual‑rate rougher flotation operational processes［J］.IEEE Transactions on Industrial Electronics，2018，65（5）：4092-4102.
7	Krizhevsky A， Sutskever I， Hinton G E.ImageNet classification with deep convolutional neural networks［J］.Communications of the ACM，2017，60（6）：84-90.
8	Zarie M， Jahedsaravani A， Massinaei M.Flotation froth image classification using convolutional neural networks［J］.Minerals Engineering，2020，155：106443.
9	Zhang Y J， Soon H G， Ye D S，et al.Powder‑bed fusion process monitoring by machine vision with hybrid convolutional neural networks［J］.IEEE Transactions on Industrial Informatics，2020，16（9）：5769-5779.
10	Wen L， Li X Y， Gao L，et al.A new convolutional neural network‑based data‑driven fault diagnosis method［J］.IEEE Transactions on Industrial Electronics，2018，65（7）：5990-5998.
11	Huang T， Zhang Q， Tang X A，et al.A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems［J］.Artificial Intelligence Review，2022，55（2）：1289-1315.
12	Cen J， Yang Z H， Liu X，et al.A review of data‑driven machinery fault diagnosis using machine learning algorithms［J］. Journal of Vibration Engineering & Technologies，2022，10（7）：2481-2507.
13	Yuan X F， Qi S B， Shardt Y A W，et al.Soft sensor model for dynamic processes based on multichannel convolutional neural network［J］.Chemometrics and Intelligent Laboratory Systems，2020，203：104050.
14	He K M， Zhang X Y， Ren S Q，et al.Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）.Las Vegas，2016：770-778.
15	Xue Z X， Yu X C， Liu B，et al.HResNetAM hierarchical residual network with attention mechanism for hyperspectral image classification［J］.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2021，14：3566-3580.
16	Jiao J Y， Zhao M， Lin J，et al.Residual joint adaptation adversarial network for intelligent transfer fault diagnosis［J］.Mechanical Systems and Signal Processing，2020，145：106962.
17	Yuan X F， Qi S B， Wang Y L.Stacked enhanced auto‑encoder for data‑driven soft sensing of quality variable［J］.IEEE Transactions on Instrumentation and Measurement，2020，69（10）：7953-7961.
18	Yu Y， Li J T， Li J C，et al.Automated damage diagnosis of concrete jack arch beam using optimized deep stacked autoencoders and multi‑sensor fusion［J］.Developments in the Built Environment，2023，14：100128.
19	Deng Z W， Wang Z Y， Tang Z H，et al.A deep transfer learning method based on stacked autoencoder for cross‑domain fault diagnosis［J］.Applied Mathematics and Computation，2021，408：126318.
20	Yuan X F， Li L， Wang Y L，et al.Deep learning for quality prediction of nonlinear dynamic processes with variable attention‑based long short‑term memory network［J］.The Canadian Journal of Chemical Engineering，2020，98（6）：1377-1389.

序号	名称	单位	序号	名称	单位
1	粗选X轴速度	cm/s	16	浮选机检测点1液位	cm
2	粗选Y轴速度	cm/s	17	浮选机检测点2液位	cm
3	粗选大泡数	个	18	浮选机检测点3液位	cm
4	粗选中泡数	个	19	浮选机检测点4液位	cm
5	粗选小泡数	个	20	浮选机检测点5液位	cm
6	粗选大泡面积	像素	21	浮选机1充气量测量值	m³/min
7	粗选中泡面积	像素	22	浮选机2充气量测量值	m³/min
8	粗选小泡面积	像素	23	浮选机3充气量测量值	m³/min
9	粗选大泡稳定性	%	24	浮选机4充气量测量值	m³/min
10	粗选中泡稳定性	%	25	浮选机5充气量测量值	m³/min
11	粗选小泡稳定性	%	26	浮选机6充气量测量值	m³/min
12	粗选泡沫稳定性	%	27	浮选机7充气量测量值	m³/min
13	粗选图像色调	°	28	浮选机8充气量测量值	m³/min
14	粗选图像饱和度	%	29	浮选机9充气量测量值	m³/min
15	粗选图像亮度	%

序号	名称	单位	序号	名称	单位
1	粗选X轴速度	cm/s	16	浮选机检测点1液位	cm
2	粗选Y轴速度	cm/s	17	浮选机检测点2液位	cm
3	粗选大泡数	个	18	浮选机检测点3液位	cm
4	粗选中泡数	个	19	浮选机检测点4液位	cm
5	粗选小泡数	个	20	浮选机检测点5液位	cm
6	粗选大泡面积	像素	21	浮选机1充气量测量值	m³/min
7	粗选中泡面积	像素	22	浮选机2充气量测量值	m³/min
8	粗选小泡面积	像素	23	浮选机3充气量测量值	m³/min
9	粗选大泡稳定性	%	24	浮选机4充气量测量值	m³/min
10	粗选中泡稳定性	%	25	浮选机5充气量测量值	m³/min
11	粗选小泡稳定性	%	26	浮选机6充气量测量值	m³/min
12	粗选泡沫稳定性	%	27	浮选机7充气量测量值	m³/min
13	粗选图像色调	°	28	浮选机8充气量测量值	m³/min
14	粗选图像饱和度	%	29	浮选机9充气量测量值	m³/min
15	粗选图像亮度	%

名称	输出维度	参数
卷积层	32×32	3×3，32，步长=2
恒等映射模块	32×32	3×3，32，步长=1
恒等映射模块	32×32	3×3，32，步长=1
恒等映射模块	32×32	3×3，32，步长=1
投影映射模块	16×16	3×3，64，步长=1
恒等映射模块	16×16	3×3，64，步长=1
恒等映射模块	16×16	3×3，64，步长=1
投影映射模块	8×8	3×3，128，步长=1
恒等映射模块	8×8	3×3，128，步长=1
恒等映射模块	8×8	3×3，128，步长=1
平均池化层	128	—
全连接层	11	—

名称	输出维度	参数
卷积层	32×32	3×3，32，步长=2
恒等映射模块	32×32	3×3，32，步长=1
恒等映射模块	32×32	3×3，32，步长=1
恒等映射模块	32×32	3×3，32，步长=1
投影映射模块	16×16	3×3，64，步长=1
恒等映射模块	16×16	3×3，64，步长=1
恒等映射模块	16×16	3×3，64，步长=1
投影映射模块	8×8	3×3，128，步长=1
恒等映射模块	8×8	3×3，128，步长=1
恒等映射模块	8×8	3×3，128，步长=1
平均池化层	128	—
全连接层	11	—

指标	方法	状态等级				加权平均
指标	方法	差	中	良	优	加权平均
精准率	ResNet	97.93	96.56	96.41	98.90	97.42
	SSPAE	92.68	96.75	97.12	98.98	96.67
	ResNet-SSPAE	93.55	98.88	96.68	98.32	97.05
	ResNet-SSPAE-AM	96.13	99.29	95.93	99.73	97.82
召回率	ResNet	97.93	97.73	97.14	97.04	97.41
	SSPAE	97.83	94.48	96.51	97.78	96.62
	ResNet-SSPAE	98.49	93.65	97.71	98.05	96.97
	ResNet-SSPAE-AM	98.21	95.31	98.67	98.72	97.78
F1-score	ResNet	97.93	97.14	96.77	97.96	97.41
	SSPAE	95.19	95.60	96.82	98.38	96.63
	ResNet-SSPAE	95.96	96.19	97.19	98.18	96.98
	ResNet-SSPAE-AM	97.16	97.26	97.28	99.22	97.78