A deep framework for predictive maintenance

Date
2021-12-01
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
ENGLISH ABSTRACT: Predictive maintenance (PdM) is a well-known maintenance approach that comprises of two problems, machine prognostic modelling and maintenance scheduling. The objective of prognostic modelling is to predict faults in machine components such as aircraft engines, lithium-ion batteries or bearings. The objective of maintenance scheduling is to reduce the cost of performing maintenance once the future degradation behaviour of a component has been established. Sensors are used to monitor the degradation behaviour of components as they change over time. Supervised learning is a suitable solution for prognostic modelling problems, especially with the increase in sensor readings being collected with Internet of Things (IoT) devices. Prognostic modelling can be formulated as remaining useful life (RUL)- or machine state estimation. The former is a regression- and the later is a classification problem. Long short-term memory (LSTM) recurrent neural networks (RNNs) are an extension of traditional RNNs that are effective at interpreting trends in the sensor readings and making longer term estimations. An LSTM uses a window of sequential sensor readings when making prognostic estimates which causes it to be less sensitive to local sensor variations, which results in improved prognostic model performance. In this study we create a framework to implement PdM approaches. The work consists of a codebase which can be used to create testable, comparable and repeatable prognostic modelling results and maintenance scheduling simulations. The codebase is designed to be extensible, to allow future researchers to standardise prognostic modelling results. The codebase is used to compare the prognostic modelling performance of an LSTM with tradition supervised prognostic modelling approaches such as Random Forests (RF)s, Gradient boosted (GB) trees and Support Vector Machines (SVM)s. The prognostic models are tested on three well-known prognostic datasets, the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) engine aircraft-, Center for Advanced Life Cycle Engineering (CALCE) battery- and Intelligent Maintenance Systems (IMS) bearing datasets. During the study we highlight factors that influence prognostic model performance, such as the effect of de-noising sensor readings and the size of the sample window used by the LSTM when making estimations. The results of the prognostic models are compared with previous studies and the LSTM shows improved performance on considered cases. The developed prognostic models are used to perform preventative maintenance scheduling with assumed costs in two simulations. The objective is first to compare the efficacy of traditional maintenance approaches, such as a mean time between failure (MTBF) strategy, with a PdM strategy, and second to investigate the effect of using a better performing prognostic model (such as the LSTM) in a PdM strategy. The improvements are measured by the reduction in costs. Key words: Predictive maintenance; remaining useful life; machine state estimation; preventative maintenance scheduling.
AFRIKAANSE OPSOMMING: Voorspellende instandhouding (PdM) is ’n bekende instandhoudingsbenadering wat bestaan uit twee probleme, naamlik masjienprognostiese modellering en instandhoudingskedulering. Die doel van prognostiese modellering is om foute in masjienkomponente soos vliegtuigenjins, litiumioonbatterye of laers te voorspel. Die doel van instandhoudingskedulering is om die koste van die uitvoering van instandhouding te verminder sodra die toekomstige degradasiegedrag van ’n komponent vasgestel is. Sensors word monitor die degradasiegedrag van komponente soos hulle verander oor tyd. Toesigleer is ’n geskikte oplossing vir prognostiese modelleringsprobleme, veral met die toename in sensorlesings wat met Internet of Things (IoT) toestelle ingesamel word. Prognostiese modellering kan geformuleer word as oorblywende nuttige lewensduur (RUL)- of masjientoestandberaming. Eersgenoemde is ’n regressie- en die latere is ’n klassifikasieprobleem. Langtermyngeheue (LSTM) herhalende neurale netwerke (RNN) is ’n uitbreiding van ’n tradisionele RNN wat effektief is om tendense in die sensorlesings te interpreteer en langertermynskattings te maak. ’n LSTM gebruik ’n venster van opeenvolgende sensorlesings wanneer prognostiese skattings gemaak word, wat veroorsaak dat dit minder sensitief is vir plaaslike sensorvariasies, wat lei tot verbeterde prognostiese modelwerkverrigting. In hierdie studie skep ons ’n raamwerk om PdM-benaderings te implementeer. Die werk bestaan uit ’n kodebasis wat gebruik kan word om toetsbare, vergelykbare en herhaalbare prognostiese modelleringsresultate en onderhoudskeduleringssimulasies te skep. Die kodebasis is ontwerp om uitbreidbaar te wees, sodat toekomstige navorsers prognostiese modelleringsresultate kan standaardiseer. Die kodebasis word gebruik om die prognostiese modelleringsprestasie van ’n LSTM te vergelyk met tradisionele prognostiese modelleringsbenaderings soos Random Forests (RF)’e, Gradient boosted (GB) trees en Support Vector Machines (SVM)’s. Die prognostiese modelle word getoets op drie bekende prognostiese datastelle, die Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) enjinvliegtuie, Sentrum vir Gevorderde Lewensiklusingenieurswese (CALCE) battery en Intelligente Onderhoudstelsels (IMS) dradatastelle. Tydens die studie beklemtoon ons faktore wat prognostiese modelprestasie beïnvloed, soos die effek van die ruisonderdrukking van sensorlesings en die grootte van die monstervenster wat deur die LSTM gebruik word wanneer ramings gemaak word. Die resultate van die prognostiese modelle word vergelyk met vorige studies en die LSTM toon verbeterde prestasie op die oorwoë gevalle. Die ontwikkelde prognostiese modelle word gebruik om voorkomende instandhoudingskedulering uit te voer met veronderstelde koste in twee simulasies. Die doelwit is eerstens om die doeltreffendheid van tradisionele-instandhoudingsbenaderings, vb. ’n gemiddelde tyd tussen mislukking (MTBF)-strategie, met ’n PdM-strategie te vergelyk en tweedens om die effek van die gebruik van ’n beter presterende prognostiese model (soos die LSTM) in ’n PdM strategie te ondersoek. PdM strategie. Die verbeterings word gemeet aan die vermindering in koste. Sleutelwoorde: Voorspellende instandhouding; oorblywende nuttige lewensduur; masjien toestand skatting; voorkomende onderhoudskedulering.
Description
Computer Science
Keywords
Preventative maintenance scheduling, Predictive control, Maintenance, Machinery -- Maintenance and repair -- Estimates, Scheduling, Supervised learning (Machine learning), Scheduling, Maintenance, Machinery -- Maintenance and repair -- Estimates
Citation