Machine learning based intelligent diagnosis methods can adaptively generate the fault diagnosis model by historical data, which have attracted much attention. Artificial neural network (ANN) is one of the most important tools for gearbox intelligent diagnosis. However, the training of ANN has the problem of local optima, and it is hard to determine the ANN structure. These problems have great influence on the diagnosis performance of ANN. In this paper, a variable neural network (RegPSOVNN) is proposed for gearbox fault diagnosis based on regrouping particle swarm optimization. Ten time-domain features are selected to form the input of the ANN. Regrouping particle swarm optimization (RegPSO) is utilized for the optimization of ANN structure and network training. It can simultaneously optimize the structure and parameters of ANN and effectively avoid the problem of local optima. To evaluate the diagnosis performance of the proposed method, gearbox failure experiments were conducted, and backpropagation neural network (BPNN), firefly variable neural network (FAVNN) and particle swarm optimization based variable neural network (PSOVNN) were used for comparison. Experimental results indicated that the proposed method can effectively optimize the network structure and diagnosis the gearbox faults.
YaoB., ZhenP., WuL., GuanY., Rolling element bearing faultdiagnosis using improved manifold learning, IEEE Access5 (2017), 6027–6035.
2.
LiC., SanchezR.-V., ZuritaG., ., Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals, Mechanical Systems and Signal Processing76-77 (2016), 283–293.
3.
EverG.I., GhaliaM.B., An automatic regrouping mechanism to deal with stagnation in particle swarm optimization, M.S. Dissertation, The University of Texas-Pan American, 2009.
4.
EverG.I., GhaliaM.B., Regrouping particle swarm optimization: Anew global optimization algorithm with improved performance consistency across benchmarks, Proceeding of IEEE International Conference on System, Man and Cybernetics (2009), 3901–3908.
5.
ShaoH., JiangH., ZhaoH., WangF., A novel deep autoencoder feature learning method for rotating machinery fault diagnosis, Mechanical Systems and Signal Processing95 (2017), 187–204.
6.
AliJ.B., SaidiL., MouelhiA., Chebe-MorelloB., FnaiechLinearF., feature selection and classification using PNN and SFAMneural networks for a nearly online diagnosis of bearing naturallyprogressing degradations, Engineering Applications of Artificial Intelligence42 (2015), 67–81.
7.
KennedyJ., EberthartR., Particle swarm optimization, Proceedings of the 6th International Symposium on Micro Machine andHuman Science (1995), 39–43.
8.
KennedyJ., EberthartR., A new optimizer using particle swarm theory, Proceeding of IEEE International Conference on Neural Network (1995), 1942–1948.
9.
KennedyJ., The particle swarm: Social adaptation of knowledge, Proceeding of IEEE International Conference on Evolutionary Computation (1997), 303–308.
10.
ZhangJ.R., ZhangJ., LokT.M., LyuM.R., A hybrid particle swarm optimization back-propagation algorithm for feed forward neuralnetwork training, Applied Mathematics and Computation185 (2007), 1026–1037.
11.
RenL., LvW., JiangS.W., XiaoY., Fault diagnosis using a jointmodel based on sparse representation and SVM, IEEE Transactionon Instrumentation and Measurement65 (2016), 2313–2320.
12.
AsrM.Y., EttefaghM.M., HassannejadR., RazaviS.N., Diagnosisof combined faults in rotary machinery by non-naive Bayesian approach, Mechanical Systems and Signal Processing85 (2017), 56–70.
13.
BarakatM., EI BadaouiM. and GuilletF., Hard competitive growingneural network for the diagnosis of small bearing faults, Mechanical Systems and Signal Processing37 (2013), 276–292.
14.
CerradaM., ZutitaG., ., Fault diagnosis in spur gears basedon genetic algorithm and random forest, Mechanical Systems and Signal Processing70-71 (2016), 87–103.
PrietoM.D., CirrinncioneG., EspinosaA.G., OrtegaJ.A. and HenaoH.H, Bearing fault detection by a novel condition-monitoring scheme based on statistical-time features and neural networks, IEEE Transaction on Industrial Electronics60 (2013), 3398–3407.
17.
WanasN., AudaG., KamelM.S., KarrayF., On the optimal numberof hidden nodes in a neural network, Proceeding of IEEECanadian Conference on Electrical and Computer Engineering (1998), 918–921.
18.
JanssensO., SlavkovikjV., VervischB., ., Convolutional neural network based fault detection for rotating machinery, Journal of Sound and Vibration377 (2016), 331–345.
19.
AlexanderP., SinghR., Gas turbine engine fault diagnostics using fuzzy concepts, Proceeding of AAIA 1st Interlligent Systems Technical Conference (2004), 1–15.
20.
HelwigS., WankaR., Theoretical analysis of initial particle swarm behavior, Proceeding of the 10th International Conferenceon Parallel Problem Solving from Nature (PPSN) (2008), 889–898.
21.
WongT.T., LukW.S., HengP.A., Sampling with Hammersley andHalton points, Journal of Graphics Tools2 (1997), 9–24.
22.
XuT., YinZ., CaiD., ZhengD., Fault diagnosis for rotatingmachinery based on local mean decomposition morphology filtering and least square support vector machine, Journal of Intelligent &Fuzzy Systems32 (2017), 2061–2070.
23.
FransV.D.B., An analysis of particle swarm optimizers, Ph.D.Dissertation, University of Pretoria; 2007.
24.
LiW., ZhangS., HeG., Semisupervised distance-preservingself-organizing map for machine-defect detection and classification, IEEE Transactions on Instrumentation and Measurement62 (2013), 869–879.
25.
LiW., ShiT., LiaoG., YangS., Feature extraction andclassification of gear faults using principal component analysis, Journal of Quality in Maintenance Engineering9 (2003), 132–143.
26.
LiW., WengS., ZhangS., A firefly neural network and itsapplication in bearing fault diagnosis, Journal of MechanicalEngineering51 (2015), 99–106.
27.
LiW., ZhangS., RakhejaS., Feature denoising andnearest-farthest distance preserving projection for machine faultdiagnosis, IEEE Transaction on Industrial Informatics12 (2016), 393–404.
28.
LiuX., DengZ., WangT., Real estate appraisal system based onGIS and BP neural network, Transaction of Nonferrous MetalsSociety of China21 (2011), s626–s630.
29.
LeiY., LinJ., HeZ., ZuoM., A review on empirical modede composition in fault diagnosis of rotating machinery, Mechanical Systems and Signal Processing35 (2013), 108–126.
30.
LeiY., JiaF., LinJ., ., An intelligent fault diagnosismethod using unsupervised feature learning towards mechanical bigdata, IEEE Transaction on Industrial Electronics63 (2016), 3137–3147.
31.
ShatnawiY., Al-KhassawenehM., Fault diagnosis in internalcombustion engines using extension neural network, IEEETransaction Industrial Electronics61 (2014), 1434–1443.
32.
ShiY., EberthartR., A modified particle swarm optimizer, Proceeding of the IEEE World Congress on Computational Intelligence (1998), 69–73.
33.
TianY., WangZ.L., LuC., Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping, Mechanical Systems and Signal Processing, In press, 2018.
34.
ChenZ., LiW., Mulitisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief neural network, IEEE Transaction in Instrumentation and Measurement66 (2017), 1693–1702.
35.
WangZ.Y., LuC., ZhouB., Fault diagnosis for rotary machinerywith selective ensemble neural network, Mechanical System andSignal Processing, In press, 2018.
