Operational Analytics for Predictive & Proactive Maintenance www.sv-europe.com A SELECT INTERNATIONAL COMPANY
Agenda • Introduction to operational & predictive analytics • Worked examples of operational analytics – Practical examples • Break • Demonstration of capabilities – Model development & text mining • Best practices & maximising success – Analytical methodology, resources & deployment • Summary & conclusion • Lunch A SELECT INTERNATIONAL COMPANY
• Premium, accredited partner to IBM specialising in the SPSS Advanced Analytics suite. • Team each has 15 to 20 years of experience working in the predictive analytic space - specifically as senior members of the heritage SPSS team A SELECT INTERNATIONAL COMPANY
What do we mean by ‘Predictive Analytics’? Predictive analytics encompasses a variety of techniques from statistics and data mining that analyze current and historical data to make predictions about future events Analysis of structured and unstructured information with mining, predictive modelling, and 'what-if?' scenario analysis. A SELECT INTERNATIONAL COMPANY
What is operational analytics for preventative maintenance? Understanding the patterns in operational data to determine the areas of greatest risk and directing resources before risk becomes reality. A SELECT INTERNATIONAL COMPANY
What do we mean by ‘predictive analytics’? • It’s different from business intelligence or MI reporting • Actually, it’s not always about prediction • However, predictive analytics does creates important new data • These data take the form of estimates, probabilities, forecasts, recommendations, propensity scores, classifications or likelihood values • Which in turn can be incorporated into key operational and/or insight systems A SELECT INTERNATIONAL COMPANY
Predictive operational analytics: industry sectors A SELECT INTERNATIONAL COMPANY
Predictive operational analytics: common applications A SELECT INTERNATIONAL COMPANY
How can operational analytics help? Finding patterns in maintenance Unearthing characteristics that lead to an operations that could point to increased frequency of failures? opportunities for improvements? Identifying factors that increase ownership cost and downtime over the life of a system / asset? Identifying assets at risk of failure Predicting impact or consequence scores to even when they have no previous enhance Alarms Management so that key alarm failure history events are prioritized Mining free text from thousands of logs that describe the maintenance performed on systems to accurately categorize maintenance reports and identify areas of risk A SELECT INTERNATIONAL COMPANY
Types of predictive modelling… Identify groups Predict a within a particular type population of outcome displaying homogeneity Propensity/ Clustering (based on a wide Classification array of data) Association / Time Series Identify Forecast a Sequence repeatable future value patterns of over a defined behaviour or time period sequence… A SELECT INTERNATIONAL COMPANY
Types of predictive modelling… • Classification / propensity – How likely is this asset (vehicle / pump / property / meter) to fail / report and issue? • Clustering – How can I divide plant / asset portfolio into meaningful and discernible groups as a framework for proactive maintenance / inspection regimes? • Association & sequence – What is the sequence & cadence of recorded events that can be identified as the antecedents of an asset failure in a specific location? • Time series – What is production line downtime going to be next month / quarter / year? A SELECT INTERNATIONAL COMPANY
Other SPSS predictive maintenance & quality customers A SELECT INTERNATIONAL COMPANY
Operational analytics: worked examples Jarlath Quinn www.sv-europe.com A SELECT INTERNATIONAL COMPANY
Effective operational analytics applications… • Weather Conditions Utilise historical data • Ambient Temperature from multiple sources… Environmental • Maintenance History • Notes from inspection • Customer Feedback Interaction • Machine • Material • Age Assets • Telemetry • Alarms • Events (Failure ,Faults) Behavioural A SELECT INTERNATIONAL COMPANY
Effective operational analytics applications… …to build accurate, testable • Weather Conditions • Ambient Temperature predictive models… Environmental • Maintenance History • Notes from inspection 19% Likelihood new filter required • Customer Feedback Interaction 22% chance of Failure • Machine • Material 0.43 probability • Age Assets of repeat error Estimated Temperature • Telemetry = 26.2 • Alarms • Events (Failure ,Faults) Behavioural A SELECT INTERNATIONAL COMPANY
Effective operational analytics applications… …to generate predictions and • Weather Conditions • Ambient Temperature risk scores …. Environmental • Maintenance History • Notes from inspection • Customer Feedback Interaction • Machine • Material • Age Assets • Telemetry • Alarms • Events (Failure ,Faults) Behavioural A SELECT INTERNATIONAL COMPANY
Effective operational analytics applications… …that can be deployed into operational systems and other insight/reporting platforms A SELECT INTERNATIONAL COMPANY
Effective operational analytics applications… …to make smarter decisions A SELECT INTERNATIONAL COMPANY
Consolidate the data that seems most relevant to the application Asset Register Meteorological/Location Data Maintenance History Load/Monitoring Data A SELECT INTERNATIONAL COMPANY
Visualise the data and identify potential predictive indicators • Corrosion/fatigue score • Average gas pressure score • • Higher the degree of corrosion Lower the sustained pressure score • Higher the risk of asset failure • Higher the risk of failure/discharge A SELECT INTERNATIONAL COMPANY
Don’t ignore unstructured data Text mining produces structured data from unstructured: example from Water Industry • “Tried to clear but they reckon its on the main sewer line - causing backup inside toilet - neighbour • “Possible discharge of across the back has been having similar problems and we found a cooking fat from lateral into blockage on the main - can we main sewer as there is a check? ” block outside the takeaway .” Text mining gives Text mining gives • Main sewer • Fat problem • Backup • Lateral sewer • Blockage • Property type A SELECT INTERNATIONAL COMPANY
Make sure the model makes sense A SELECT INTERNATIONAL COMPANY
Example of an actual reusable predictive model A SELECT INTERNATIONAL COMPANY
Model evaluation: what does ‘success’ look like? Model classification • 84% accuracy in predicting asset failure • Chart shows strong correlation between estimated risk of failure and actual failures A SELECT INTERNATIONAL COMPANY
What does ‘deployment’ look like? • Assets in red have a high risk profile but no previous issues A SELECT INTERNATIONAL COMPANY
Model scores open new doors of insight • Risk becomes a new dynamic metric • Risk can be viewed in terms of – – projected spend – asset value – failure consequence – maintenance cost A SELECT INTERNATIONAL COMPANY
Let’s See A Demonstration www.sv-europe.com A SELECT INTERNATIONAL COMPANY
Cell site maintenance A SELECT INTERNATIONAL COMPANY
Best Practice www.sv-europe.com A SELECT INTERNATIONAL COMPANY
What are the common ingredients of successful applications? Using multiple data sources • Fixed attributes • Dynamic attributes – Asset data – Maintenance history • Model type/class – Usage history • Specification – Part replacements – Weight – Maintenance reports (free text ) – Size – Operating environment – Range Environmental/ Asset data Maintenance Usage telematics history A SELECT INTERNATIONAL COMPANY
What are the common ingredients of successful applications? Utilising a powerful, proven methodology 1.Business – CRISP-DM: Cross Industry Standard Understanding Process for Data Mining 2.Data 6.Deployment Understanding 3.Data 5.Evaluation Preparation 4.Modelling http://crisp-dm.eu/ A SELECT INTERNATIONAL COMPANY
1.Business Understanding 2.Data 6.Deployment Understanding 3.Data 5.Evaluation Preparation 4.Modelling 2 4 5 3. Data Preparation 6 1 Time A SELECT INTERNATIONAL COMPANY
The CRISP-DM process 1.Business Understanding 2.Data 6.Deployment Understanding 3.Data 5.Evaluation Preparation 4.Modelling A SELECT INTERNATIONAL COMPANY
Recommend
More recommend
