Skip to main content

Hybridization of harmonic search algorithm in training radial basis function with dynamic decay adjustment for condition monitoring

Abstract

In recent decades, hybridization of superior attributes of few algorithms was proposed to aid in covering more areas of complex application as well as improves performance. Condition monitoring is a major component in predictive maintenance which monitors the condition and identifies significant changes in the machinery parameter to perform early detection and prevent equipment defects that could cause unplanned downtime or incur unnecessary expenditures. An effective condition monitoring model is helpful to reduce the frequency of unexpected breakdown incidents and thus, facilitates in maintenance. ANN has shown effective in various condition monitoring and fault detection applications. ANN is popular due to its capability of identifying the complex nonlinear relationships among features in a large dataset and hence, it can perform with an accurate prediction. However, a drawback is that the performance of ANN is sensitive to the parameters (i.e., number of hidden neurons and the initial values of connection weights) in its architecture where the settings of these parameters are subject to tuning on a trial-and-error basis. Hence, a wide range of studies have been focused on determining the optimal weight values of ANN models and the number of hidden neurons. In this research work, the motivation is to develop an autonomous learning model based on the hybridization of an adaptive ANN and a metaheuristic algorithm for optimizing ANN parameters so that the network could perform learning and adaptation in a more flexible way and handle condition classification tasks more accurately in industries, such as in power systems. This paper presents an intelligent system integrating a Radial Basis Function Network with Dynamic Decay Adjustment (RBFN-DDA) with a Harmony Search (HS) to perform condition monitoring in industrial processes. RBFN-DDA performs incremental learning wherein its structure expands by adding new hidden units to include new information. As such, its training can reach stability in a shorter time compared to the gradient-descent based methods. To achieve optimal RBFN-DDA performance, HS is proposed to optimize the center and the width of each hidden unit in a trained RBFN. By integrating with the HS algorithm, the proposed metaheuristic neural network (RBFN-DDA-HS) can optimize the RBFN-DDA parameters and improve classification performances from the original RBFN-DDA by 2.2% up to 22.5% in two benchmarks datasets, which are numerical records from a bearing and steel plate system and a condition-monitoring system in a power plant (i.e., the circulating water (CW) system). The results also show that the proposed RBFN-DDA-HS is compatible, if not better than, the classification performances of other state-of-the-art machine learning methods.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Data availability

1. The bearing dataset analyzed during the current study is available in the bearing data center of Case Western Reserve University (CWRU) https://csegroups.case.edu/bearingdatacenter/home. 2. The steel plate dataset analyzed during the current study is available in the UCI repository https://archive.ics.uci.edu/ml/datasets/steel+plates+faults. 3. The circulating water (CW) system dataset analyzed during the current study is not publicly available due the copyright is owned by the power generation plant but is available from the corresponding author on reasonable request.

Code availability

NA.

References

  • Abualigah LM, Khader AT, Hanandeh ES (2018a) A combination of objective functions and hybrid Krill herd algorithm for text document clustering analysis. Eng Appl Artif Intell 73:111–125

    Google Scholar 

  • Abualigah LM, Khader AT, Hanandeh ES (2018b) A new feature selection method to improve the document clustering using particle swarm optimization algorithm. J Comput Scince 25:456–466

    Google Scholar 

  • Abualigah L et al (2021a) Aquila optimizer: a novel meta-heuristic optimization algorithm. Comput Ind Eng 157:107250

    Google Scholar 

  • Abualigah L et al (2021b) The arithmetic optimization algorithm. Comput Methods Appl Mech Eng 376:113609

    MathSciNet  MATH  Google Scholar 

  • Ahmad R, Akhtar N, Choubey N (2017) Applications of artificial bee colony algorithms and its variants in health care. Bio-Chem Indian J 11(1):110

    Google Scholar 

  • Ahmadi MA et al (2018) An accurate model to predict drilling fluid density at wellbore conditions. Egypt J Pet 27(1):1–10

    MathSciNet  Google Scholar 

  • Ali YH (2018) Artificial intelligence application in machine condition monitoring and fault diagnosis. Artif Intell Emerg Trends Appl 275

  • Azzini A, Tettamanzi AG (2011) Evolutionary ANNs: a state of the art survey. Intell Artif 5(1):19–35

    Google Scholar 

  • Barreto AM, Barbosa HJ, Ebecken NF (2002) Growing compact RBF networks using a genetic algorithm. In: VII Brazilian symposium on neural networks, 2002. SBRN 2002. Proceedings. IEEE

  • Ben Ali J et al (2015) Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals. Appl Acoust 89:16–27

    Google Scholar 

  • Berthold MR, Diamond J (1998) Constructive training of probabilistic neural networks. Neurocomputing 19(1):167–183

    Google Scholar 

  • Bhoskar MT et al (2015) Genetic algorithm and its applications to mechanical engineering: a review. Mater Today Proc 2(4–5):2624–2630

    Google Scholar 

  • Bi TS et al (2000) A novel ANN fault diagnosis system for power systems using dual GA loops in ANN training. In: 2000 power engineering society summer meeting (Cat. No.00CH37134)

  • Blanchard BS (2004) Logistics engineering and management. Pearson Prentice Hall, Hoboken

    Google Scholar 

  • Cerrada M et al (2018) A review on data-driven fault severity assessment in rolling bearings. Mech Syst Signal Process 99:169–196

    Google Scholar 

  • Cocconcelli M et al (2011) Diagnostics of ball bearings in varying-speed motors by means of artificial neural networks. In: Proceedings of the 8th international conference on condition monitoring and machinery failure prevention technologies

  • Daliri S (2020) Using harmony search algorithm in neural networks to improve fraud detection in banking system. Comput Intell Neurosci 2020:6503459

    Google Scholar 

  • de Castro LN, Von Zuben FJ (2001) An immunological approach to initialize centers of radial basis function neural networks. In: Proceedings of CBRN’01 (Brazilian conference on neural networks)

  • Devikanniga D, Vetrivel K, Badrinath N (2019) Review of meta-heuristic optimization based artificial neural networks and its applications. J Phys Conf Ser 1362:012074

    Google Scholar 

  • Ding SX et al (2011) A survey of the application of basic data-driven and model-based methods in process monitoring and fault diagnosis. IFAC Proc Vol 44(1):12380–12388

    Google Scholar 

  • Ding S et al (2013) Evolutionary artificial neural networks: a review. Artif Intell Rev 39(3):251–260

    Google Scholar 

  • Do QH (2017) Predictions of machine vibrations using artificial neural networks trained by gravitational search algorithm and back-propagation algorithm. Intelligence 15(1):93–111

    Google Scholar 

  • Geem ZW, Kim JH, Loganathan G (2001) A new heuristic optimization algorithm: harmony search. SIMULATION 76(2):60–68

    Google Scholar 

  • Geem Z, Kim J, Loganathan G (2002) Application of harmony search algorithm to water resources problems. In: Conference of the environmental and water resources institute of ASCE, ASCE, Roanoke, USA

  • Gertler J (1998) Fault detection and diagnosis in engineering systems. Taylor & Francis, Milton Park

    Google Scholar 

  • Gunerkar RS, Jalan AK, Belgamwar SU (2019) Fault diagnosis of rolling element bearing based on artificial neural network. J Mech Sci Technol 33(2):505–511

    Google Scholar 

  • Hamadneh N et al (2012) Learning logic programming in radial basis function network via genetic algorithm. J Appl Sci (faisalabad) 12(9):840–847

    Google Scholar 

  • Hesser DF, Markert B (2019) Tool wear monitoring of a retrofitted CNC milling machine using artificial neural networks. Manuf Lett 19:1–4

    Google Scholar 

  • Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press, Ann Arbor

    MATH  Google Scholar 

  • Horng M-H et al (2012) Firefly meta-heuristic algorithm for training the radial basis function network for data classification and disease diagnosis. INTECH Open Access Publisher

  • Hudak MJ (1992) Rce classifiers: theory and practice. Cybern Syst 23(5):483–515

    MathSciNet  Google Scholar 

  • Illias HA, Chai XR, Abu Bakar AH (2016) Hybrid modified evolutionary particle swarm optimisation-time varying acceleration coefficient-artificial neural network for power transformer fault diagnosis. Measurement 90:94–102

    Google Scholar 

  • Isermann R (1997) Supervision, fault-detection and fault-diagnosis methods—an introduction. Control Eng Pract 5(5):639–652

    Google Scholar 

  • Kankar PK, Sharma SC, Harsha SP (2012) Vibration-based fault diagnosis of a rotor bearing system using artificial neural network and support vector machine. Int J Model Identif Control 15(3):185–198

    Google Scholar 

  • Karaboga D (2005) An idea based on honey bee swarm for numerical optimization. Technical report-tr06, Erciyes university, engineering faculty: Kayseri, Turkey

  • Karayiannis NB (1999) Reformulated radial basis neural networks trained by gradient descent. IEEE Trans Neural Netw 10(3):657–671

    Google Scholar 

  • Kassim N et al (2014) Harmony search-based optimization of artificial neural network for predicting AC power from a photovoltaic system. In: Power engineering and optimization conference (PEOCO), 2014 IEEE 8th international, 2014. IEEE

  • Kattan A, R. Abdullah (2013) Training feed-forward artificial neural networks for pattern-classification using the harmony search algorithm. In: The second international conference on digital enterprise and information systems (DEIS2013). The Society of Digital Information and Wireless Communication

  • Kavathekar S, Upadhyay N, Kankar P (2016) Fault classification of ball bearing by rotation forest technique. Procedia Technol 23:187–192

    Google Scholar 

  • Khilar PM, Dash T (2020) Multifault diagnosis in WSN using a hybrid metaheuristic trained neural network. Digit Commun Netw 6(1):86–100

    Google Scholar 

  • Kok JN et al (2009) Artificial intelligence: definition, trends, techniques, and cases. Artif Intell 1:270–299

    Google Scholar 

  • Kurban T, Beşdok E (2009) A comparison of RBF neural network training algorithms for inertial sensor based terrain classification. Sensors 9(8):6312–6329

    Google Scholar 

  • Lee KS et al (2005) The harmony search heuristic algorithm for discrete structural optimization. Eng Optim 37(7):663–684

    MathSciNet  Google Scholar 

  • Lee A, Geem ZW, Suh K-D (2016) Determination of optimal initial weights of an artificial neural network by using the harmony search algorithm: application to breakwater armor stones. Appl Sci 6(6):164

    Google Scholar 

  • Lei Y et al (2010) A multidimensional hybrid intelligent method for gear fault diagnosis. Expert Syst Appl 37(2):1419–1430

    Google Scholar 

  • Lei Y et al (2014) Condition monitoring and fault diagnosis of planetary gearboxes: a review. Measurement 48:292–305

    Google Scholar 

  • Lichman M (2013) UCI machine learning repository. 2013, University of California, Irvine, School of Information and Computer Sciences

  • Liu Y et al (2004) Training radial basis function networks with particle swarms. In: International symposium on neural networks Springer

  • Loparo KA (2003) Bearing vibration data set

  • Mahdavi M, Fesanghary M, Damangir E (2007) An improved harmony search algorithm for solving optimization problems. Appl Math Comput 188(2):1567–1579

    MathSciNet  MATH  Google Scholar 

  • Manjunath T, Kusagur A (2018) Analysis of different meta heuristics method in intelligent fault detection of multilevel inverter with photovoltaic power generation source. Int J Power Electron Drive Syst 9(3):1214

    Google Scholar 

  • Marwala T, Vilakazi CB (2007) Computational intelligence for condition monitoring. arXiv:0705.2604

  • Miljković D (2011) Fault detection methods: a literature survey. In: 2011 proceedings of the 34th international convention MIPRO

  • Mohanty AR (2014) Machinery condition monitoring: principles and practices. CRC Press, Boca Raton

    Google Scholar 

  • Muruganatham B et al (2013) Roller element bearing fault diagnosis using singular spectrum analysis. Mech Syst Signal Process 35(1–2):150–166

    Google Scholar 

  • Patton RJ, Frank PM, Clark RN (2013) Issues of fault diagnosis for dynamic systems. Springer, Berlin

    Google Scholar 

  • Robnik-Šikonja M (2016) Data generators for learning systems based on RBF networks. IEEE Trans Neural Netw Learn Syst 27(5):926–938

    MathSciNet  Google Scholar 

  • Sheng W et al (2011) RBF neural network parameters optimization based on paddy field algorithm. In: 2011 IEEE international conference on information and automation

  • Shi HW (2010) ACO trained ANN-based intelligent fault diagnosis. Appl Mech Mater 20–23:141–146

    Google Scholar 

  • Siddhpura A, Paurobally R (2013) A review of flank wear prediction methods for tool condition monitoring in a turning process. Int J Adv Manuf Technol 65(1–4):371–393

    Google Scholar 

  • Simon D (2002) Training radial basis neural networks with the extended Kalman filter. Neurocomputing 48(1):455–475

    MATH  Google Scholar 

  • Singh GK (2003) Induction machine drive condition monitoring and diagnostic research—a survey. Electric Power Syst Res 64(2):145–158

    Google Scholar 

  • Sivakumar M, Parvathi R (2014) Application of neural network trained with meta-heuristic algorithms on fault diagnosis of muti-level inverter. Res J Appl Sci 9(6):369–375

  • Stephens MP (2010) Productivity and reliability-based maintenance management. Purdue University Press, West Lafayette

    Google Scholar 

  • Tallam RM, Habetler TG, Harley RG (2003) Stator winding turn-fault detection for closed-loop induction motor drives. IEEE Trans Ind Appl 39(3):720–724

    Google Scholar 

  • Tan SC, Lim CP (2004) Application of an adaptive neural network with symbolic rule extraction to fault detection and diagnosis in a power generation plant. IEEE Trans Energy Convers 19(2):369–377

    Google Scholar 

  • Tan SC, Lim CP (2015) Evolving an adaptive artificial neural network with a gravitational search algorithm. In: Intelligent decision technologies. Springer, pp 599–609

  • Tan SC, Lim CP, Rao MVC (2007) A hybrid neural network model for rule generation and its application to process fault detection and diagnosis. Eng Appl Artif Intell 20(2):203–213

    Google Scholar 

  • Tenaga Nasional Berhad (1999) System description and operating procedures. Prai Power Station Stage 3

  • Tidriri K et al (2016) Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: a review of researches and future challenges. Annu Rev Control 42:63–81

    Google Scholar 

  • Vakharia V, Gupta VK, Kankar PK (2016) A comparison of feature ranking techniques for fault diagnosis of ball bearing. Soft Comput 20(4):1601–1619

    Google Scholar 

  • Venkatasubramanian V, Rengaswamy R, Kavuri SN (2003a) A review of process fault detection and diagnosis. Comput Chem Eng 27(3):313–326

    Google Scholar 

  • Venkatasubramanian V et al (2003b) A review of process fault detection and diagnosis. Comput Chem Eng 27(3):293–311

    MathSciNet  Google Scholar 

  • Venkatasubramanian V et al (2003c) A review of process fault detection and diagnosis. Comput Chem Eng 27(3):327–346

    MathSciNet  Google Scholar 

  • Waeyenbergh G, Pintelon L (2002) A framework for maintenance concept development. Int J Prod Econ 77(3):299–313

    Google Scholar 

  • Wang G, Yang Y, Guo Z (2013) Hybrid learning based Gaussian ARTMAP network for tool condition monitoring using selected force harmonic features. Sens Actuators A 203:394–404

    Google Scholar 

  • Wong SY (2015) Novel extreme learning machines for pattern classification, data regression, and rules generation, in College Of Engineering. Universiti Tenaga Nasional, Kajang

    Google Scholar 

  • Woolson R (2007) Wilcoxon signed-rank test. Wiley, Hoboken, pp 1–3

    Google Scholar 

  • Xiao Y, Feng L (2012) A novel neural-network approach of analog fault diagnosis based on kernel discriminant analysis and particle swarm optimization. Appl Soft Comput 12(2):904–920

    Google Scholar 

  • Xin Y (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447

    Google Scholar 

  • Yao X (1993) A review of evolutionary artificial neural networks. Int J Intell Syst 8(4):539–567

    Google Scholar 

  • Yin S et al (2014) A review on basic data-driven approaches for industrial process monitoring. IEEE Trans Ind Electron 61(11):6418–6428

    Google Scholar 

  • Yu B, He X (2006) Training radial basis function networks with differential evolution. In: Proceedings of IEEE international conference on granular computing. 2006. Citeseer

  • Zaiping C et al (2008) Neural network electrical machine faults diagnosis based on multi-population GA. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence)

  • Zaranezhad A, Mahabadi HA, Dehghani MR (2019) Development of prediction models for repair and maintenance-related accidents at oil refineries using artificial neural network, fuzzy system, genetic algorithm, and ant colony optimization algorithm. Process Saf Environ Prot 131:331–348

    Google Scholar 

  • Zhou H et al (2016) Effective calculation model of drilling fluids density and ESD for HTHP well while drilling. In: IADC/SPE Asia Pacific drilling technology conference, 2016. Society of Petroleum Engineers

Download references

Acknowledgements

The authors would like to acknowledge the Ministry of Higher Education of Malaysia for the financial support under the Fundamental Research Grant Scheme (FRGS), Grant No: FP061-2015A and also the Ministry of Education Malaysia for the financial support under the program myBrain15.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Hwa Jen Yap.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Chong, H.Y., Tan, S.C. & Yap, H.J. Hybridization of harmonic search algorithm in training radial basis function with dynamic decay adjustment for condition monitoring. Soft Comput 25, 10221–10235 (2021). https://doi.org/10.1007/s00500-021-05963-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-021-05963-3

Keywords

  • Metaheuristic
  • Radial Basis Function Network
  • Condition monitoring
  • Harmony search
  • Optimization