Abstract
This paper presents a novel online learning-based fault detection designed for underwater robotic thruster health monitoring. In the fault detection algorithm, we build a mathematical model between the control variable and the propeller speed by fitting collected online work status data to the model. To improve the accuracy of online modeling, a multi-center PSO algorithm with memory ability is utilized to optimize the modeling parameters. Additionally, a model online update mechanism is designed to accommodate the model to the change of thruster work status and sea environment. During the operation, propeller speed of the underwater robot is predicted through the online learning-based model, and the model residuals are used for thruster health monitoring. To avoid false alarm, an adaptive fault detection strategy is established based on model online update mechanism. The proposed method has been extensively evaluated using different underwater robotics, through a sea trial data simulation, a pool test fault detection experiment and a sea trial fault detection experiment. Compared with fixed model-based method, speed prediction MAE of the online learning model is at least 37.9% lower than that of the fixed model. The online learning-based method show no misdiagnosis in experiments, while the fixed model-based method is misdiagnosed. Experimental results show that the proposed method is competitive in terms of accuracy, adaptability, and robustness.
Highlights
Underwater robotics has come to play an increasingly important role in sea exploration
In order to ensure the accuracy of the online modeling of the control variable–speed model, we propose the use of an improved particle swarm optimization (PSO) algorithm, which is suitable for online applications, for online optimization to achieve the appropriate selection of model order and modeling data volume
The pipeline of thTeheupnidpeerliwneatoefrthroebuontdicesrwthartuerstreorbofatiucsltthdreutsetcetriofanuilmt dpelteemctieonntaimtiopnlemisentation is illustrated in Figuirlleu6st.rBateefdorien fFaiuglutrde e6t.ecBtieofonr,ethfaeuhltisdteotreicctaiol nb,etshtesohliusttoiroincallibbreastrysowluatsioinnil-ibrary was tialized based on pinriitoiarlikznedowblaesdedgeoonfptrhieorthkrnuoswtelerdmgeodoef lt.hDe uthrirnugsteorpmeroadtieoln. oDfutrhineguonpdeerra-tion of the water robot, the suynsdteemrwamteornriotbooritn, tgheinsfyosrtemmatmioonniwtoarisngcoinllfeocrtmedat,iownhwicahs cwolalescfted, iwnhtoichthweas fed into online learning-batsheedofnaliunlet ldeeatrencintigo-nbaaslegdofraiuthltmd.etection algorithm
Summary
Underwater robotics has come to play an increasingly important role in sea exploration. In data-driven approach-based fault detection methods, a large amount of data is required for model training, in order to satisfy underwater application requirements. In [6], a propeller fault detection method based on an energy consumption model is proposed, using a data-driven strategy. In [33], a data-driven multivariate regression approach based on long short-term memory with residual filtering (LSTM-RF) is proposed to fulfill UAV fault detection and recovery. In order to perform fault detection in the presence of ocean current interference and real-time state changes, we propose an online learning-based fault detection method for. In order to perform fault detection in the presence of ocean current interference oafn2d9 real-time state changes, we propose an online learning-based fault detection method for underwater robotic thruster systems. TThhee rreesstt ooff tthhee ppaappeerriissoorrggaannizizeeddaassfofolllolowws.s.InInSeSceticotnion3, 3th, ethoenolinnleineesteimstiamtioatnioonf toifmteimdeeladyelianyreilnatrieolnattiootnhetothtrhuesttehrrsuysstteermsyisstdeemscirsibdeeds.cIrnibSeedct.ioInn4S, ethcteioonnli4n, ethmeoodnelliinnge bmeotwdeleingcobnetwroelevnacroianbtlreosl avnardiarbolteastiaonndsrpoeteadtioins sinptereodduisceindt,roadnudcemdu, latin-cdemntuerltip-caerntitceler spwaratricmleospwtiamrmizaotpiotinmiiszauttiiolinzeisduttoiloizpetdimtoizoeptthime mizeodtheel pmaoradmeleptearsa.mInetSeersc.tiIonnS5e,cthioeno5n,ltihne monoldineel mupoddaetleumpdeactheamniescmhains iisnmtroisdiunctreodd. uInceSde. cItnioSnec6t,iotnhe6,etxhpeeerixmpernitmalenptlaltfpolramtfoirsmdeissdcersibcreidb,eadn, dantdhethseasetraiatrlsiaalsndanpdopool otelsttessatsrearaenanlyazlyedze. dSe. cSteioctnio7nc7oncoclnucdlueds ethsethweowrko.rk
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call