a diag no nostic maint ntena nanc nc e system
play

A DIAG NO NOSTIC MAINT NTENA NANC NC E SYSTEM FOR C C - PowerPoint PPT Presentation

A DIAG NO NOSTIC MAINT NTENA NANC NC E SYSTEM FOR C C OMMERIC IAL A L AND N D NAVAL L VESSELS LS J ANE C C ULLU LLUM SU SUPERVISO SORS: S: jane ne.cul ullum um@ut utas.edu. u.au Associate Professor J onathan Binns,


  1. A DIAG NO NOSTIC MAINT NTENA NANC NC E SYSTEM FOR C C OMMERIC IAL A L AND N D NAVAL L VESSELS LS J ANE C C ULLU LLUM SU SUPERVISO SORS: S: jane ne.cul ullum um@ut utas.edu. u.au Associate Professor J onathan Binns, Professor Kiril Tenekedjiev, Dr. Rouzbeh Abbassi, Dr. Vikram G araniya, Michael Lonsdale

  2. 2 C OMMERC IAL AL AN AND N NAV AVAL AL VES ESSEL EL M MAINTEN ENANC E: E: Sta tate te-of of-the he-ar art 1. 1. Periodi dic pl planned d maint ntena nanc nce a and nd RC C M M a are not ot op optimal but wor ork 2. 2. Limited dat ata a an and know owledge ge of of how ow to to inte terpret i t it 3. 3. No n need eed f for innov ovation on? HMAS SI S SIRIUS 4. 4. Appl pplications? HMAS SI S SIRIUS S AND HMAS M S MELBOURNE C APT APT AI AIN C O O K G G R AV AVING DO C K, S S O O UT H C C HINA S S E E A, 2017 A NS W, 2014 2014

  3. 3 C HALLENG ES: C ONDI DITI TION B BASED D AND D PRED EDIC TIVE M E MAINTEN ENANC E ▪ Har ardwar are e an and I Infras astructure e – Mobile as e asset et, mar aritime e en environmen ent ▪ Usef eful d dat ata ▪ Qua uant ntity ▪ Inter erpret etat ation

  4. 4 C HALLEN ENG ES ES: DATA INTER ERPRET ETATION ▪ Meani ning ngful ul inter erpret etat ation o of d dat ata ▪ Ide deni nitfying ng mai ainten enan ance e tas asks Exper ert Exper erien ence e - Man anual al Rel eliab ability C C en entred ed Mai ainten enan ance e - Man anual al Diag agnostic S System em – Automat atic (can an al also be p e par art of RC M)

  5. 5 5 HMAS W WALLE LLER SYDNEY Y HARBOUR, N NSW G OALS? S? Improve e av avai ailab ability an and red educe o e over eral all m mai ainten enan ance e cost Improve m maint ntena nanc nce s sche hedul duling ng speed eed and c nd cons nsistenc ncy

  6. 6 DIA IAG NOSTIC IC MAINT NTENA NANC NC E S SC HEDULING NG ▪ Diagnose machine health, risk of failure … ▪ Schedule maintenance if if and when en required PM Interval PM Interval PM Interval IONS PM Interval PM Interval PM Interval TIO IC PREDIC System Interval C System Interval B System Interval A ENTS Interval C Interval A Interval B EQUIREMEN Sche hedul ule m maint ntena nanc nce onl nly w whe hen n req equired ed REQ

  7. 7 DIAG NOSTIC NO MAINT NTENA NANC NC E S SYSTEM FOR OR A C OM OMMERC IAL OR OR NAVAL V VESSEL C OM OMPON ONENT 2. Mai ainten enan ance e 1. Risk sk A Asse ssessm ssment - Sche hedul uling ng - C ondition Monitoring and Decision Theory Machine Learning C OM OMPONENT APPL PPLIC ATION FRAMEWORK NUMBER ER 2 G EN ENER ERAL SER ERVIC E E PUMP C OMPONENT APPLIC ATION 3. Per erforman ance e Measurem emen ent - Availability and O verall VAL VALUE = T TRAN ANSLAT ATE + S SC AL ALE + FOREC AST AS Maintenance C ost Is it BETTE TTER TH THAN periodic PM?

  8. 8 VAL VALUE I IN TRAN ANSLAT ATION FOR C C OMMERC IAL O OR NAVA AVAL VE VESSEL AP APPLIC AT ATIONS HTA EL ELWING HTA W WAREE 1. C reate system at component level 2. Tune and re-use for similar components on same or different vessels eg. Estimate system reduces maintenance cost of pump by 10% below current PM: Per Pump : ~$80 AUD per year Total for HTAs, 6 pumps : ~$500 AUD per year Total RAN Fleet – 49 ships, boats, submarines, 10 pumps per vessel: ~$40,600 AUD per year

  9. 9 VAL VALUE I IN SC AL ALE FOR C C OMMERC IAL O OR NAVA AVAL VE VESSEL AP APPLIC ATIONS AT Fleet eet 1. C reate systems at component level for high priority components Ves essel el Ves essel el Ves essel el 2. Integrate systems to create higher Sub-sy Su syst stem 1 1 Sub-sy Su syst stem 2 2 levels using RC M or alternatives C ompon om onent 1 1 Add individual component savings C om ompon onent 2 2

  10. 10 10 Reliability of of C om ompon onent vs. Time ASTING 1.2 1 0.8 ity ilit iabil FOREC EC 0.6 Relia 0.4 0.2 E IN F 0 0 5 10 15 20 25 VALUE Time Ti Corrosion Wear Fatigue Eac ach s set et o of dat ata a points can an b be g e gen ener erat ated ed using system em at at t time t e t, w wher ere e R = 1 1 – F (m (mode(t (t)), )), also r rec ecommen ends an action and t ther eref efore m e mainten enance e cost 10 of 18

  11. 10 10 C OM OMPLETED W WOR ORK TO M O MARC H 2018 DA DATA TA C OLLEC TION TI • Designed ten experiments, procured and installed hardware, completed experimental data collection and processing • Designed C M data collection process, procured and installed hardware, completed 65% of data collection • Wrote scripts for data processing (experimental and C M) • C ompiled equipment and maintenance data to date for Number 2 G eneral Service Pump • C ompleted survey of C hief Engineer METHOD ODOL OLOG OG Y • Identified novelty and strengths of methodology using literature review process • Developed new decision modelling theory in conjunction with supervisor (focus of second paper) • Designed and wrote scripts for methodology WRITTE TTEN C OMMUNIC ATI TION OF F RESEARC H • Literature review paper published in Ocean Engineering J ournal • Internal Serco Hub article on research • C ompleted second paper draft – currently under review by supervisor • Drafted four chapters of Thesis 12

  12. 11 11 RE REMAINING W WORK RK DA DATA TA C C OLLEC TI TION • [September 2018] C omplete remaining 2/3 of C M – 8 fortnightly sessions - 8 hours total time • Process remaining CM data • Record recommendations of Engineer and preventative maintenance alongside system recommendations METHOD ODOL OLOG OG Y • Tune model • Generate recommendations from CM data using tuned model • Graph recommendations from methodology, Engineer and PM schedule, calculate availability and maintenance cost of the three policies WRITTE TTEN C OMMUNIC ATI TION OF F RESEARC H • Complete second paper draft and submission • Complete results paper draft and submission • Complete thesis 13

  13. 12 12 C OMPON OM ONENT A APPLIC ATION ON: NUMBER ER 2 2 G EN ENER ERAL S SER ERVIC E E PUMP 13 13 1. 1. Risk sk A Asse ssessm ssment - C ondition Monitoring and Machine Learning a. Data for Algorithm Training and C ondition Monitoring 13 b. Machine Learning E xamples 23 c. Applying a Machine Learning Algorithm 24 25 25 2. 2. Maint ntena nanc nce Sche hedul uling ng - Decision Theory a. Maintenance Actions as Lotteries 25 b. Modelling Lottery Prizes: Multi-attribute Utility 26 c. Making a Decision: Maximum E xpected Utility 27 28 28 3. 3. Per erforman ance M e Meas easurem emen ent - Availability and Overall Maintenance C ost Availability and Maintenance C ost, Validation 28

  14. 13 13 DAT ATA F A FOR M MAC AC HINE L LEAR ARNING AND ND C C OND NDITION M N MONI NITORING NG C REA EATE E DATASET ETS DES ESC RIBING C OMMON C C ENTRIFUG EN AL P PUMP T wo P o Purpos oses: FAULTS: S: 1. From Experiments on 1. 1. No f fau ault – Run pump under normal operational conditions al alongside Test Pump- Build 2. 2. No f fau ault – Run pump under normal operational conditions eng ngine nes r runni unning ng model 3. 3. No f fau ault – Run pump under normal operational conditions at at s sea ea 2. From Condition 4. 4. Worn I Impel eller er - Lathe impeller fluid side and polish Monitoring on No. 2 5. 5. Worn b bear earing – Measure pump bearing with many running hours General Service Pump 6. 6. Dam amag aged ed b bear earing – Grind outer race of new bearing flat and polish – Use model to predict 7. 7. Unbal alan anced ed s shaf aft/ Stat atic Imbal alan ance e – Lathe off material from one point of shaft 8. 8. Misal aligned ed s shaf aft/ Offset et m misal alginmen ent – Misalign pump-motor coupling condition of No. 2 9. 9. Loose p e pac acking – Loosen casing bolts G eneral service pump 10. Poor 10. oor m mou ounting – Loosen mounting bolt on pump foot

  15. 14 14 DAT ATA F A FOR M MAC AC HINE L LEAR ARNING AND ND C C OND NDITION M N MONI NITORING NG THE E DATASET ETS (20 min s sessions): S SAMPLE E RATE: E: T wo P o Purpos oses: 1. Vibration: Dual channel on pump Every 2 minutes 1. From Experiments on Test Pump- Build 2. Temperature: Thermal imaging camera Per Minute model 2. From Condition 3. Pressure: Suction and discharge gauges Per Minute Monitoring on No. 2 General Service Pump 4. Motor current: Current clamp on cord Per Minute – Use model to predict condition of No. 2 5. Packing drip rate: Visual inspection Per Minute G eneral service pump 6. Shaft rotation: Tacometer Per experiment

  16. 15 15 ELWING EL BILG E/ E/ FIRE E SYSTEM EM TEMPOR ORARY C ON ONFIG URATION ON Operating c g con ondition ons for or all pu pumps ps: -0.2 bar Suction 2.1 bar Discharge

  17. 16 16 TE TEST T PUMP S SETU TUP NUMBER ER 2 G EN ENER ERAL SER ERVIC E E PUMP

  18. 17 17 TE TEST R T RIG S SETU TUP

Recommend


More recommend