Predictive Maintenance by analysing acoustic data in an industrial environment
11 likes3,598 views
This document discusses predictive maintenance through acoustic data analysis in an industrial setting. It describes using sensors and data collection from machines to detect potential issues through acoustic and vibration analysis. The customer case study involves implementing a predictive maintenance platform using acoustic data from an air compressor to identify mechanical, electrical, and other problems to decrease maintenance costs and increase machine availability. The solution involves collecting machine and sensor data, storing it in an IIoT platform, and performing analytics using predictive models and dashboards.
Predictive Maintenance by analysing acoustic data in an industrial environment
- 1. Predictive maintenance by analyzing acoustic data in an industrial environment Philippe Duhem June 2016 CONNECT ACTTHINK
- 2. 2© Sogeti High Tech 2© Sogeti High Tech Production equipment management Building management Inventory management Delivery tracking Production of customized products Operational excellence Remote product upgrades Remote maintenance Data insights for engineering Product improvements Pay per use models Lease + maintain vs. sell New business models IoT use cases *Source: McKinsey By 2025, IoT will have pervasive impact in Manufacturing with a $2.5 trillion* impact & over 50% around operational excellence (TBC!) IoT impact in Manufacturing for the next 10 years
- 3. What’s new ? 3© Sogeti High Tech Sensors, PLC, Machine data Physical Models Simulation behaviors Empirical models, Tests data Scientific software Pre & Post treatment Adapting the model to real behaviors Thresholds, alarms CAX HPC LSF Family, PBS, SGE, SLURM Dedicated infrastructure Physical engineering: Structural, Thermal, CFD, EM, Acoustics, Vibration, … Sources Treatment Infra What Sensors, PLC, Machine data Operators data Quality data, TRS, Maintenance Raw material, Traceability, Tests Statistic analysis Machine Learning, Clustering, Forecast, Decision trees Linear regressions, Neuronal network NoSQL DB, Distributed computing framework Cloud Probability Predictive models Recommendations MODEL DRIVEN DATA DRIVEN
- 4. Manufacturing Intelligence & Predictive Maintenance 4© Sogeti High Tech Monitor and control production units based on factual decisions as defined by all collected data Reduce non quality costs Decrease Non OEE Master standard cycle time Optimize consumption (raw material, energy…) Production teams will quickly identify key factors impacting production objectives Physical engineering: Structural, Thermal, CFD, EM, Acoustics, Vibration, … Use case Business Values Output How Predict potential breakdowns of a machine through data analysis Decrease Non OEE Reduce maintenance costs Maintenance teams will anticipate preventive activities Predictive models Dashboard Recommendations MANUFACTURING INTELLIGENCE PREDICTICE MAINTENANCE
- 5. Troubleshooting by data acoustic analytics 5© Sogeti High Tech Our Customer operates production units of energy located in France. The objective was to decrease the maintenance costs by optimizing the maintenance activities and machines availability rates Experiment acoustic and vibration troubleshooting Implement a global predictive maintenance platform The target machine for the first stage is a high-powered air compressor. It represents a strategic and critical asset for the production units The noise and vibration troubleshooting are used to identify mechanical, electrical, hydraulics and aerodynamics problems. The method is based on a comparison of noise and vibration spectra with an acoustic and vibration database Data storage: The measurement data with an operational context Maintenance & Machine Data Platform: Acquisition & collect: open, scalable, secure Analytics platform hosted in a cloud A rapid implementation: platform available in 1 month, models ready to use in 2 months Relevant statistic model supported by a model driven approach Scalable and secured solution based on an IIOT architecture Hybrid Cloud with operational treatments in the customer premises and analytics in the CloudBenefits Solution Issue
- 6. Manufacturing Intelligence & Predictive Maintenance 6© Sogeti High Tech Web Mobile DataConcentrator Data Pipelines Routing Transformation Mediation logic Time Series NoSQL Relational In Memory Files Search Processing Analysis & Usage Data LakeData Ingestion – IIoTData Sources - IIoT
- 7. IIoT Platform eObject: from edge to analytics 7© Sogeti High Tech IoT MODULES FUNCTIONS DESCRIPTION1. 2. 3. FEATURES4 e-OBJECT Edge Data acquisition • A software Agent is embedded on : objects (Sensors, devices, gateways) with communication, security and processing services. 1 Data storage & administration • A Middleware Platform collects & stores of large amount of data. • Devices & sensors managing services. • Hosted in a public or private cloud e-OBJECT Cloud2 Data analysis & visualization • An Analytics Platform analyses data from multi sources/multi files. • Data are transformed into information displayed on a visual interface. e-OBJECT Analytics3
- 8. IoT Architecture 8© Sogeti High Tech ActionAssignmentAnalysisAggregationAcquisition Business Services Core Business Services Big Data Analytics EngineData LakeM2M Layer Connectivity Device Management System Monitoring & Control Orchestration Storage Fusion Correlation Analytics Predictive Models Visualisation/ Dashboard Real-time Monitoring Benchmark Trends Forecasts +++… Industrial Building Infrastructure Predictive Maintenance Manufacturing & Storage Metering Tracking & positioning Smart Grid eObject PlatformEdge Applications Data Sources Security Management Cloud Management Smart Building ERP GMAO MES
- 9. Build on micro-services 9© Sogeti High Tech Choose the right service for the right use Interconnect to build your application Use the best of each pool Acquisition eObject IIOT Storage Analytics Data Visualization Structuring IoT
- 10. MIPM deployment phases 10© Sogeti High Tech DATA COLLECTION DATA STRUCTURATION MODEL & ANALYSE DEPLOY & IMPROVE OBJECTIVES & DATA IDENTIFICATION Define clear objectives Identify if relevant data are available Prepare Change MIPM DEPLOYMENT Industrial IS Machines connected Data collection Secure & scalable Data structuration Data Lake Analytics platform Monitoring Modeling Dashboarding Deployment Adapt, optimize Change management
- 11. Contact information 11© Sogeti High Tech Philippe DUHEM IoT & Mobility Business Developer philippe.duhem@sogeti.com Tél. : +33 34 46 91 52 Mob: +33 (0)6 32 94 09 55 SOGETI High Tech Bat. Aeropark 3 Chemin Laporte 31300 TOULOUSE
- 12. www.sogeti-hightech.fr The information contained in this presentation is proprietary. © 2016 Sogeti High Tech. All rights reserved.. Fort de 4000 collaborateurs, Sogeti High Tech met son expérience et ses compétences en Ingénierie, Informatique Technique & Industrielle et Digital Manufacturing au service des secteurs aéronautique, spatial, défense, énergie, transport. Depuis 30 ans, Sogeti High Tech est le partenaire de ses clients industriels sur des missions de bout-en-bout, depuis le conseil, la conception, la mise en œuvre, le déploiement, la sécurisation et le test de solutions techniques complexes à haute valeur ajoutée, jusqu’au maintien en conditions opérationnelles puis le retrait de service des installations. Sogeti High Tech dispose de programmes de R&D embarqués afin d’anticiper les mutations technologiques et leurs usages dans l’environnement industriel. Sogeti High Tech est par ailleurs porteur pour le groupe Capgemini de la plateforme IoT « e-Object » pour le secteur Energy&Utilities.