verticale

Nuove tecnologie per l’asset monitoring di beni industriali: il caso Flowserve

- National Instruments –Company introduction
- Monitoring challenges in Industrial IoT
- Asset Maintenance: technology wave for a new strategy
- Case Study: FlowServe IIoT solution

Scarica il PDF Scarica il PDF
Aggiungi ai preferiti Aggiungi ai preferiti


Atti di convegni o presentazioni contenenti case history
SAVE ottobre 2017 Asset Management: Leva Competitiva per il Manifatturiero Intelligente

Pubblicato
da Benedetta Rampini
SAVE 2017Segui aziendaSegui




Settori: 

Parole chiave: 


Estratto del testo
Veronafiere 18-19 ottobre 2017 Gli atti dei convegni e pi di 8.000 contenuti su www.verticale.net Cogenerazione Termotecnica Industriale Pompe di Calore 27 ottobre Cogenerazione Termotecnica Industriale Pompe di Calore Alimentare Alimentare Petrolchimico Alimentare 28 ottobre Alimentare Petrolchimico Alimentare Alimentare Petrolchimico Visione e Tracciabilit 28 ottobre Luce Energia Domotica LED Luce Energia Domotica LED ni.com Claudio Cupini National Instruments Italy Field Marketing Engineer - Embedded Control & Monitoring claudio.cupini@ni.com Nuove Tecnologie per l'Asset Monitoring Il Caso Flowserve Agenda ' National Instruments ' Company introduction ' Monitoring challenges in Industrial IoT ' Asset Maintenance: technology wave for a new strategy ' Case Study: FlowServe IIoT solution ni.com NI equips engineers and scientists with systems that
accelerate productivity, innovation, and discovery. Mission Statement Accelerating Engineering for More Than Four Decades 2020 1986 LabVIEW starts the computer-based measurement revolution 1991 Creates the Alliance Partner Network to strengthen ecosystem 1998 Creates PXI and expands opportunities with complete system solutions 2004 Makes FPGAs accessible to engineers and scientists 2006 Announces CompactDAQ to increase measurement accuracy 2013 Introduces software-designed instrumentation 2014 Leads prototyping of 5G systems 1976 NI founded 1977 Introduces GPIB to connect instruments to mini computers 1983 Introduces first GPIB board to connect instruments to IBM PCs 1987 Releases data acquisition solutions to provide accurate measurements ~50% OF CONNECTED DEVICES DEPLOYED BETWEEN 2015 AND 2025 WILL BE INDUSTRIAL 50 BILLION CONNECTED DEVICES BY 2020 'Cisco 'IHS Markit Cisco, The Internet of Things: How the Next Evolution of the Internet Is Changing Everything, 2011 IHS Markit, IoT Trend Watch 2017 Industrial IoT Architecture Operational Assets Transportation and Heavy Equipment Production
Equipment Test Assets THINGS OF THE IIOT Sensors and Actuators Edge Nodes OPERATIONAL TECHNOLOGY (OT) On-Premises Cloud INFORMATION TECHNOLOGY (IT) Industrial IoT Architecture Sensors and Actuators Edge Nodes On-Premises Cloud Operational Assets Transportation and Heavy Equipment Production
Equipment Test Assets THINGS OF THE IIOT OPERATIONAL TECHNOLOGY (OT) INFORMATION TECHNOLOGY (IT) 'Global processing industries have reported losing $20 billion (USD) each year (or nearly 5 percent
of their total production) due to unscheduled downtime; 80 percent of those losses are preventable.' 'ARC Advisory Group 'Ninety-five percent of business leaders expect their company to use the IIoT within the next three years,
and 87 percent believe that it will contribute to long- term job growth.' 'Accenture ARC Advisory Group, Passing the Insurance Acid Test with APM, 2011
Accenture, Connected Business Transformation: How to Unlock Value From the Industrial Internet of Things, 2017 'Unscheduled shutdowns, coupled
with poor maintenance practices,
cost global process industries 5% of
total production annually, equivalent
to $20B each year.
'Hydrocarbon Publishing Company Maintenance Pain Points Higher risk of catastrophic failure New technology is more complex, expensive, and tougher to maintain Vibration specialists are hard to find and existing ones are retiring Aging plants have critical equipment that needs to be reliable SAFETY! Unable to get to all the necessary measurements we need Inconsistent diagnostics Spending too much time collecting vs. analyzing data Lack of insight to understand overall reliability Disparate systems Maintenance Strategy Objectives Increase Revenue ' Increase uptime and service offerings ' Optimize maintenance activities Decrease Cost ' Reduce frequency of unscheduled downtime ' Decrease warranty costs ' Optimize workforce Reduce Risk ' Prevent failure and unscheduled outages ' Reduce worker contact with hazardous machines and
environments Data Collection and Analysis Challenge Time spent collecting data Data actually analyzed 80% 5% It is difficult to locate, hire, and train new equipment specialists to periodically collect data who can use their experience to diagnose machine issues. Source: NI customers and the International Data Corporation (IDC) Source: Allied Reliability Group Maintenance Managers Who Are Not Happy
With Their Current Maintenance Approach Why' 1. Too many resources and lack of results with time and money spent 2. Unexpected [and costly] equipment failures still occur 78% '1 out of every 3 dollars spent on
preventative maintenance is wasted.' Online Monitoring Benefits Optimized Workforce ' Maintenance staff spends time assessing required
maintenance Fewer Gaps in Data ' Continuous data collection reduces probability of data
errors or missed events Improved Diagnostics ' Consistent analysis and more historical trend data
reduce reliance on experience of equipment specialists NI InsightCM Components ASSETS OPERATIONAL TECHNOLOGY (OT) INFORMATION TECHNOLOGY (IT) NI CONFIDENTIAL NI InsightCM' ' Configuration-based acquisition and data
management tools ' Wide range of dynamic waveform and static
sensor input options ' Data storage and visualization ' Complete accessibility to data ' Connectivity to third-party systems and
analytics via LabVIEW Configuration-based tools tailored for online monitoring applications NI Monitoring Devices
Integrated sensor measurements, analytics, data storage, and alarming Native sensor support:
' Accelerometers
' Velometers
' Proximity Probes
' Tachometers
' Current Transducer
' Potential Transducer
' Static voltage
' Static current (4-20 mA)
' RTD
' Thermocouple
' Digital input
' Modbus Electrical with MCSA (Motor Current Signature Analysis) Vibration and Process 19 The NI Edge Node Advantage Nanosecond
Analysis and Control N Data Acquisition From
Any Sensor D Open Connected
Software O Edge-Ready
Hardware E Synchronized Data and
Edge Node Hardware S NI InsightCM' Software Configuration-based data acquisition, storage, and visualization tools Remote access with no client install Asset-centric configuration experience Data management &
viewers Protect system with
permissions Deployment-ready
software Alarm management tools Systems management tools Historian communication ni.com From the Edge to the Enterprise The IoT Ecosystem THINGS INFORMATION Specialist Operators Manager On Cloud On Premise INFORMATION TECHNOLOGY (IT) Data Management Machine Learning Mobile Communication Next Generation Technology Analysis Augmented Reality Visualization Data Management Visualization THINGS OF THE IIOT OPERATIONAL TECHNOLOGY (OT) INFORMATION TECHNOLOGY (IT) Sensors and Actuators Edge Nodes On-Premises Cloud Deployment Deploymen Data Management Analytics and Machine Learning Data Acquisition Control Processing and Feature Extraction Communication Security 1 PUMP/MOTOR SKID 20.7 GB / Day How Big is Big Analog Data' 1 POWER PLANT 1.6 TB / Day Data Scales With Systems Edge Analytics 10101100
11011010
11001101 Data Flow Server Analytics 10101100
11011010
11001101 Data Flow Decision Screen for Important Data Aggregate and screen along the path from edge to cloud. ' Reduce file sizes ' Lowers bandwidth required Benefits ' Processing needed ' Know the phenomena of interest Requirements Where to Store' Quick Access Full Data Aggregation THE EDGE INTERMEDIATE NETWORK/CLOUD ' Optimize network/processing bandwidth ' Data stored locally if network is down Benefits ' Local storage (volatile or non-volatile) ' Processing capability to manage file
storage and transmission arbitration Requirements Store and Forward Architecture Database Technologies ' No license to purchase (free but not free) ' Often low level tools available/needed ' SW/HW platform support hit or miss Open Source ' Features and support targeted at
industries/applications/hardware ' Lower risk of implementation with a
proven product and support ' Often has partner support Vendor Supported 20% time spent analyzing data Big Data Problem 80% time spent manually collecting data 5% of all data is actually analyzed 22% is documented well enough to be analyzed Automating Large Dataset Analysis Search Files Extract Relevant Data Analyze Place Files in Central Location Applications of Automated Intelligence Analytics and Machine Learning Visualization THINGS OF THE IIOT OPERATIONAL TECHNOLOGY (OT) INFORMATION TECHNOLOGY (IT) Sensors and Actuators Edge Nodes On-Premises Cloud Data Management Data Acquisition Control Processing and Feature Extraction Communication Security Deployment Data Managemen Analytics and Machine Learning Data Collection is More than Sensory Data Data Collection RAW DATA Sensory data
' Vibration ' Power ' Imaging ' Temperature ' Pressure ' Flow ' ' Testing Data Training Data (set aside) Operational data
' Maintenance and repair history ' Failure data ' Operating states Feature Values: Summary Information Data Collection RAW DATA Extract summary information from raw data Extract Features FEATURE VALUES Key features extracted
' Vibration ' Electrical power ' Single-point values Store feature values in an easily accessible
and documented format for later use! Reduce the Dimensions in the Data Data Collection RAW DATA Apply algorithms to combine feature values into separable regions Extract Features FEATURE VALUES Feature Reduction FEATURE VECTOR Machine Learning Projection of feature vector in 2D space X ' Training a Candidate Model Data Collection RAW DATA Apply machine learning algorithms to feature vector Extract Features FEATURE VALUES Feature Reduction FEATURE VECTOR Machine Learning Train Model CANDIDATE MODEL Baseline
Health assessment
Anomaly detection Diagnostic
Fault detection
Risk assessment Prognostics
Remaining useful life Generating Actionable Information From New Data Data Collection RAW DATA Extract Features FEATURE VALUES Feature Reduction FEATURE VECTOR At Edge Evaluate Model MODEL OUTPUT ' Failure
probability ' Detect fault ' Identify fault ' Remaining
useful life ' ' Visualization THINGS OF THE IIOT OPERATIONAL TECHNOLOGY (OT) INFORMATION TECHNOLOGY (IT) Sensors and Actuators Edge Nodes On-Premises Cloud Analytics and Machine Learning Data Acquisition Control Processing and Feature Extraction Communication Security Deployment Data Management Visualizatio Analytics and Machine Learning Superimposing computer graphics onto a live view of the world. Also known as 'AR'. WHAT IS AUGMENTED REALITY' What does AR do' AR enables faster visual processing of contextualized IIoT information Source: McKinsey Global Institute Analysis 2015 ThingWorx Studio for Augmented Reality Create Experiences Consume Experiences Manage and Deliver Experiences ThingMark Identify and track Things The IoT Ecosystem THINGS INFORMATION Specialist Operators Manager On Cloud On Premise INFORMATION TECHNOLOGY (IT) Data Management Machine Learning Mobile Communication Next Generation Technology Analysis Augmented Reality Visualization The IoT Ecosystem THINGS IT Infrastructure Measurement Platforms Data Management IIoT and Analytics INFORMATION Specialist Operators Manager On Cloud On Premise Automated Failure Predictions of Pumps 16,000 Employees 5 Billion Annual Revenue 220+ Years in Business Automated Failure Predictions for Pumps HPE Edgeline PTC ThingWorx LabVIEW and CompactRIO Flowserve Pump Pressure Temperature Power Vibration Flow Data NI InsightCM' ' ' OSI soft PI Automated Intelligence with a Smart Pump Data Collection RAW DATA Extract Features FEATURE VALUES Feature Reduction FEATURE VECTOR CompactRIO + LabVIEW Evaluate Model MODEL OUTPUT PTC ThingWorx Baseline
Alarming Diagnostic
Cavitation,
misalignment, low flow Prognostics
Remaining useful life Waveforms: accelerometers, voltage, current
Single Point: temperature, pressure, flow RMS, Peak-Peak, Crest Factor, 1x Magnitude,
Frequency, temperature, pressure, flow' Smart Pump Demonstrator 'The pump is not operating
within its normal conditions.' 'The pump has a
misalignment condition.' 'The pump wil fail in 5 days.' ni.com The Flowserve Smart Monitoring Solution - Video The NI IIoT Lab ' Innovation and Collaboration Claudio Cupini claudio.cupini@ni.com ni.com/insightcm


In evidenza

ExxonMobil
Grassi Mobil™ - Formulati per fornire elevate prestazioni anche in condizioni operative estreme
SD Project
SPAC : Il Software per la progettazione Elettrica
2G Italia
Cogenerazione e trigenerazione dal leader tecnologico mondiale
select * from VERT_CONTENUTI as con left join VERT_UTENTI_AZIENDE as azi on con.iduteazienda = azi.iduteazienda where testataurl like '%%' or eventourl like '%'%' or testataurl like '%'eiomfiere.it%' or eventourl like '%'eiomfiere.it'%'
Array ( ) Array ( [0] => Array ( [0] => 42000 [SQLSTATE] => 42000 [1] => 102 [code] => 102 [2] => [Microsoft][ODBC Driver 13 for SQL Server][SQL Server]Incorrect syntax near 'eiomfiere'. [message] => [Microsoft][ODBC Driver 13 for SQL Server][SQL Server]Incorrect syntax near 'eiomfiere'. ) [1] => Array ( [0] => 01000 [SQLSTATE] => 01000 [1] => 16954 [code] => 16954 [2] => [Microsoft][ODBC Driver 13 for SQL Server][SQL Server]Executing SQL directly; no cursor. [message] => [Microsoft][ODBC Driver 13 for SQL Server][SQL Server]Executing SQL directly; no cursor. ) )
© Eiom - All rights Reserved     P.IVA 00850640186