Studies on fault diagnosis of dissolved oxygen sensor based on GA-SVM

Pu Yang; Zhenbo Li; Yaguang Yu; Jiahui Shi; Ming Sun; Pu Yang; Zhenbo Li; Yaguang Yu; Jiahui Shi; Ming Sun

doi:10.3934/mbe.2021021

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 1: 386-399. doi: 10.3934/mbe.2021021

Previous Article Next Article

Research article Special Issues

Studies on fault diagnosis of dissolved oxygen sensor based on GA-SVM

1.
College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China
2.
National Innovation Center for Digital Fishery, China Agricultural University, Beijing 100083, China
3.
Beijing Engineering and Technology Research Centre for Internet of Things in Agriculture, Beijing 100083, China
4.
Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture, Beijing 100083, China

Received: 24 August 2020 Accepted: 25 November 2020 Published: 04 December 2020

The present research envisaged the analysis of the dissolved oxygen fault of the water quality monitoring system using the genetic algorithm-support vector machine (GA-SVM). The real-time data collected by the dissolved oxygen sensor was classified into the fault types. The fault types were divided into complete failure fault, impact fault, and constant output fault. Based on the fault classification of the dissolved oxygen parameters, SVM fault diagnosis experiments were conducted. Experimental results show that the accuracy of dissolved oxygen was 98.53%. On comparison with the experimental results of the back propagation (BP) neural network, it was found that the diagnosis results of the dissolved oxygen parameters using SVM were better than those of the BP neural network. The genetic algorithm (GA) was used to optimize the parameters. After iteration, the optimal parameters such as C and g were selected (C is the penalty coefficient, which adjusts the weight of the two index preferences in the optimization direction, i.e., the tolerance for errors, and g is a parameter that comes with the function that implicitly determines the distribution of the data after mapping to the new feature space.). By using GA, after iteration, the optimized values of C and g was found to be 2.1649 and 5.3312, respectively. The experimental results showed that the method exhibited a good accuracy.
- dissolved oxygen,
- fault diagnosis,
- support vector machine,
- genetic algorithm,
- prediction accuracy
Citation: Pu Yang, Zhenbo Li, Yaguang Yu, Jiahui Shi, Ming Sun. Studies on fault diagnosis of dissolved oxygen sensor based on GA-SVM[J]. Mathematical Biosciences and Engineering, 2021, 18(1): 386-399. doi: 10.3934/mbe.2021021

Related Papers:

Abstract

The present research envisaged the analysis of the dissolved oxygen fault of the water quality monitoring system using the genetic algorithm-support vector machine (GA-SVM). The real-time data collected by the dissolved oxygen sensor was classified into the fault types. The fault types were divided into complete failure fault, impact fault, and constant output fault. Based on the fault classification of the dissolved oxygen parameters, SVM fault diagnosis experiments were conducted. Experimental results show that the accuracy of dissolved oxygen was 98.53%. On comparison with the experimental results of the back propagation (BP) neural network, it was found that the diagnosis results of the dissolved oxygen parameters using SVM were better than those of the BP neural network. The genetic algorithm (GA) was used to optimize the parameters. After iteration, the optimal parameters such as C and g were selected (C is the penalty coefficient, which adjusts the weight of the two index preferences in the optimization direction, i.e., the tolerance for errors, and g is a parameter that comes with the function that implicitly determines the distribution of the data after mapping to the new feature space.). By using GA, after iteration, the optimized values of C and g was found to be 2.1649 and 5.3312, respectively. The experimental results showed that the method exhibited a good accuracy.

References

[1]	S. Huang, Analysis and research on the application of water quality reference materials in environmental monitoring quality control, Environ. Dev., 31 (2019), 147+149.
[2]	J. Liu, Z. Z. Lin, Analysis of the significance of water quality monitoring in environmental engineering, Resour. Conserv. Environ. Prot., 12 (2019), 54.
[3]	N. Zhang, Y. H. Yang, Design and implementation of water quality monitoring system based on internet of things, Mod. Electro. Technol., 42 (2019), 38-41+45.
[4]	D. Q. Zhu, S. L. Yu, Overview of knowledge-based fault diagnosis methods. J. Anhui Univ. Technol., 19 (2002), 197-204.
[5]	Y. Zhang, Y. Zhang, F. S. Wen, W. Z. Sun, C. Wang, Analytical model of power system fault diagnosis based on information theory, Power Autom. Equip., 34 (2014), 158-164.
[6]	F. Ding, Combined state and least squares parameter estimation algorithms for dynamic systems, Appl. Math. Modell., 38 (2014), 403-412. doi: 10.1016/j.apm.2013.06.007
[7]	F. Y. Xiao, Multi-sensor data fusion based on the belief divergence measure of evidences and the belief entropy, Inf. Fusion, 46 (2019), 23-32. doi: 10.1016/j.inffus.2018.04.003
[8]	C. S. Jonny, S. Abhinav, B. Edward, G. Kai, A knowledge-based system approach for sensor fault modeling, detection and mitigation, Expert Syst. Appl., 39 (2012), 10977-10989.
[9]	P. Baldi, M. Blanke, P. Castaldi, N. Mimmo, S. Simani, Fault diagnosis for satellite sensors and actuators using nonlinear geometric approach and adaptive observers, Int. J. Robust Nonlinear Control, 29 (2018), 5429-5455.
[10]	S. M. M. Alavi, S. Fekriasl, S. N. Niyakan, M. Saif, Fault detection and isolation in batteries power electronics and chargers. J. Energy Storage, 25 (2019), 1-9.
[11]	Y. Y. Zhang, Research on mechanical fault diagnosis method based on deep self-encoder, Huazhong Univ. Sci. Technol., 2019.
[12]	C. Wang, Z. C. Fu, H. S. Chen, G. Cui, Low-cost lockstep EDDI: instantaneous fault detection mechanism of processor, Chin. J. Comput., 35 (2012), 2562-2572. doi: 10.3724/SP.J.1016.2012.02562
[13]	Q. Zhou, Research on machine tool fault diagnosis knowledge modeling and configurable system construction method, Chongqing Univ., 2018.
[14]	Y. Wang, Fault diagnosis analysis of polarographic dissolved oxygen sensor based on deep learning, Shandong Agric. Univ., 2020.
[15]	L. L. Wang, X. H. Liu, M. Mi, Q. F. Zhang, Y. P. Zong, Y. F. Zhang, Development and Application of Seawater Nitrate Sensor Based on Spectroscopy, Transducer Microsyst. Technol., 33 (2014), 75-77+81.
[16]	Y. G. Wei, Y. S. Jiao, D. An, D. Li, W. Li, Q. Wei, Review of dissolved oxygen detection technology: from laboratory analysis to online intelligent detection, Sensors, 19 (2019), 125-134. doi: 10.3390/s19010125
[17]	J. F. Wang, C. Bian, J. H. Tong, J. Sun, Y. Li, W. Hong, et al., Modification of graphene on ultramicroelectrode array and its application in detection of dissolved oxygen, Sensors, 15 (2014), 382-393. doi: 10.3390/s150100382
[18]	A. Ma, N. S. Dinesh, K. R. Rajanna, Application of EMPC for precise position control of DC-motor system with Backlash, Control Eng. Pract., 100 (2020), 92-98.
[19]	V. N. Tan, H. Cheolkeun, Experimental study of sensor fault-tolerant control for an electro-hydraulic actuator based on a robust nonlinear observer, Energies, 12 (2019), 156-164. doi: 10.3390/en12010156
[20]	S. S. Keerthi, C. J. Lin, Asymptotic behaviors of support vector machines with Gaussia kernel, Neural comput., 15 (2003), 1667-1689. doi: 10.1162/089976603321891855
[21]	Y. Zhang, M. Martínez-García, S. R. Kalawsky, A. Latimer. Grey-box modelling of the swirl characteristics in gas turbine combustion system, Measurement.151 (2020) 107266.
[22]	Y. J. Ma, W. X. Yun, Research progress of genetic algorithm, Appli. Res. Comput., 29 (2012), 1201-1206+1210.

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)