Challenge Summary
Welcome to "PAM Wind - Power BI Dviz Design Concepts Challenge". In this challenge, we are looking to explore design concepts for a new Data Visualization Dashboard that will be implemented using "Microsoft Power BI". In this challenge, we are going to design the Data Visualization experience that will allow the user to improve the overall productivity of the WTG (Wind Turbine Generator) by evaluating the condition of the internal components, anomalous behavior, and risk of failure. By analyzing condition, anomalies, risk at the component level and rolled over to WTG helps to predict the probability of failures, that further helps to prevent the breakdowns and thereby improving productivity.
We recommend you to start by digging into data visualization design best practices, research Microsoft Power BI and think about simple ways to provide data visualization experiences.
We are really excited to kick off this new DViz Design Concepts Challenge.
- As a part of your checkpoint submission, you must upload your submission to MarvelApp so we can provide direct feedback on your designs.
- Make sure to include a URL/comment the link to your marvelapp while uploading your submission
- Make sure all pages have the correct flow! Use correct file numbering. (00, 01, 02, 03)
- As a part of your checkpoint submission, you must upload your submission to MarvelApp so we can provide direct feedback on your designs.
- Make sure to include a URL/comment the link to your marvelapp while uploading your submission
- Make sure all pages have the correct flow! Use correct file numbering. (00, 01, 02, 03)
Problem:
At Present Wind Turbines have a maintenance strategy that is centered around calendar-based maintenance and reactive maintenance after a failure has already occurred.
Solution:
The client is planning to reduce breakdown maintenance by adopting the predictive maintenance approach.
What is Predictive Asset Management?
This use case focuses on improving the overall productivity of the WTG (Wind Turbine Generator) by evaluating the condition of the internal components, anomalous behavior, and risk of failure. By analyzing condition, anomalies, risk at the component level and rolled over to WTG helps to predict the probability of failures, that further helps to prevent the breakdowns and thereby improving productivity.
Predictive maintenance is performed while the equipment is operating normally to avoid the consequences of unexpected breakdowns, increased costs, and downtime. To enable Operations & Maintenance teams to:
- Understand the real operational condition of the WTG (Wind Turbine Generator)
- Manage anomalies before they become alarms thus reducing downtime, extending asset life and improving asset performance.
- Schedule WTG maintenance based on actual asset condition as opposed to scheduled and reactive maintenance.
Design Considerations
- We are looking for a simple, easy-to-use, Informative, modern design.
- Try not to have too much information on your dashboard, you can make them compelling by making the visualization interactive and enable users to walk through or drill into the different insights.
- Use color, visual comparison, and drill-down charts to highlight comparison.
- Have your designs of size: 1366 x 768px (Desktop only, Power BI is responsive by nature so just need to design/ build once)
Power BI Requirements:
- All principles of good UX design e.g. minimize user clicks, make the experience more intuitive, minimal time to reach desired selection criteria, and performance, good color, and font themes etc., these are all critical success factors for this challenge.
- Needs to follow Power BI Design Best Practices and also take a look at the Design Tips
- Please do some research on the Power BI software and get familiar with its purpose, limitations, and what's possible.
Required Dashboard Designs
1. Condition Monitoring Dashboard:
The Condition of the Asset / Component will be at its best when it is new but gradually deteriorates with age, operating conditions, weather conditions, Load etc. Hence it is important to know the speed at which the component is deteriorating and the factors responsible for the same. This dashboard will allow the user to monitor the asset health condition for key non-structural components.
The condition monitoring results are to be displayed in the form of dashboards. The dashboard visualization will be done at these hierarchical levels
- “Fleet > Model > Site > Turbine > System > Component > Subcomponent wise
(we have shared an image to show this structure and also we have shared the possible screens at each level - it is just for reference, we are looking for better UI/UX and also make sure it is compatible with Power BI)
NOTE: User should be able to drill-down or up the hierarchy, please see the additional info document provided in challenge assets in forums!
- At each level, the dashboard should show the estimate for the remaining life for the component.
- Each component will have a score that will indicate the “component condition” beyond which the component may fail.
- Display the status with a dot for each component. Dot essentially displays the condition of the component in the Red, Yellow and Green.
- If there is a condition-deterioration pattern, then we will need to show alerts to the maintenance personnel for corrective action to prevent the failures. Once the corrective action is taken, the dashboard should reflect the updated condition score and risk scores.
- Show heat map visualization showcasing results of asset health condition scores.
- Predicting probable cause (RCA - Root Cause Analysis) for yellow and red condition and propose action if any - Systematic Approach to understand what caused the Machine to Fail.
- Think through on what filters, the search would need to be put up!
- Provide an option to download, export the report.
~
Fleet Level: In this level, we show the list of fleets and with a number of turbines with condition status for the selected fleet.
Site Level: In this level, we show the list of sites and also the number of turbines in green. Yellow and red status"
Turbine Level: In this level, we show the list of turbines in that particular site with “Condition Score, Probability of Failure and Remaining Useful life”
System Level: In this level, we show the list of systems in that particular turbine with “Condition Score, Probability of Failure and Remaining Useful life” along with the number of components in various status (green. Yellow and red)
Component Level: In this level, we show the list of Components in that particular system with “Condition Score, Probability of Failure and Remaining Useful life and RCA (this shows the probable cause for this condition)”
Sub-Component Level: In this level, we show the list of Components in that particular system with “Condition Score, Probability of Failure and Remaining Useful life and RCA (this shows the probable cause for this condition)”
2. Anomaly Detection:
Anomaly is defined as any deviation from the reference. Components tend to show anomalous behavior due to various factors like the deterioration of the health, Load, wear and tear etc. It is important to analyze the anomalous behavior and the route cause for the anomaly. Once the route cause is known then corrective actions can be carried out to avoid failures.
Anomaly Detection will be done at the component and subcomponent Level, please see 09 Output Calculation.png to understand in which level it is calculated.
(We have shared the possible screens at each level - it is just for reference, we are looking for better UI/UX and also make sure it is compatible with Power BI)
- Develop a model to identify the anomalies at the component level and subcomponent level by comparing the real time performance parameter values with the optimum operating values discovered from the historical SCADA data.
- Model should detect the performance deviation from current operating values with that of the reference parameters.
- Model should be able to provide root cause analysis for the deviation from the established threshold. By identifying the anomalous point in the parameter, one can identify the root cause for the anomaly.
- Develop and display the performance deviation in operating parameter values in the form of a graph for each component for historical SCADA data..
- Predicting probable cause (RCA) for the Anomaly and propose action if any.
- Think through on what filters, the search would need to be put up!
- Provide an option to download, export the report.
~
Important:
- Keep things consistent. This means all graphics styles should work together.
- All of the graphics should have a similar feel and general aesthetic appearance.
- Focus on User Experience / how the user interacts within the dashboard.
Reference
Example dashboards design reference for your considerations:
- https://community.powerbi.com/t5/Data-Stories-Gallery/bd-p/DataStoriesGallery
- https://docs.microsoft.com/en-us/power-bi/service-dashboard-create
- https://id.pinterest.com/steffuhnee/power-bi-dashboards/?lp=true
- https://dribbble.com/powerbidesign
MarvelApp Prototype
- We need you to upload your screens to the Marvel App
- Please send your Marvel app request to csystic@gmail.com (challenge copilot)
- You MUST include your Marvel app URL in notes /comments while uploading (in your marvelapp prototype, click on share and then copy the link & share it within your notes while you upload).
Target Audience
- Operations and Maintenance Team
Judging Criteria
- How well you plan the user experience and capture your ideas visually.
- Cleanliness of your graphics and design.
- Overall design, UI and user experience.
- Consistency across the UX/UI
Submission & Source Files
Preview Image
Please create your preview image as one (1) 1024x1024px JPG or PNG file in RGB color mode at 72dpi and place a screenshot of your submission within it.
Submission File
- Submit JPG/PNG for your submission files
- Submit Marvelapp as part of your submission.
Source Files
All original source files of the submitted design. Files should be created in Adobe Photoshop, Illustrator, XD, or Sketch!
Final Fixes
As part of the final fixes phase, you may be asked to modify your graphics (sizes or colors) or modify overall colors. We may ask you to update your design or graphics based on checkpoint feedback.
We recommend you to start by digging into data visualization design best practices, research Microsoft Power BI and think about simple ways to provide data visualization experiences.
We are really excited to kick off this new DViz Design Concepts Challenge.
Round 1
Submit your initial designs for a checkpoint feedback- As a part of your checkpoint submission, you must upload your submission to MarvelApp so we can provide direct feedback on your designs.
- Make sure to include a URL/comment the link to your marvelapp while uploading your submission
- Make sure all pages have the correct flow! Use correct file numbering. (00, 01, 02, 03)
Round 2
Submit your final designs with all checkpoint feedback implemented.- As a part of your checkpoint submission, you must upload your submission to MarvelApp so we can provide direct feedback on your designs.
- Make sure to include a URL/comment the link to your marvelapp while uploading your submission
- Make sure all pages have the correct flow! Use correct file numbering. (00, 01, 02, 03)
Problem:
At Present Wind Turbines have a maintenance strategy that is centered around calendar-based maintenance and reactive maintenance after a failure has already occurred.
Solution:
The client is planning to reduce breakdown maintenance by adopting the predictive maintenance approach.
What is Predictive Asset Management?
This use case focuses on improving the overall productivity of the WTG (Wind Turbine Generator) by evaluating the condition of the internal components, anomalous behavior, and risk of failure. By analyzing condition, anomalies, risk at the component level and rolled over to WTG helps to predict the probability of failures, that further helps to prevent the breakdowns and thereby improving productivity.
Predictive maintenance is performed while the equipment is operating normally to avoid the consequences of unexpected breakdowns, increased costs, and downtime. To enable Operations & Maintenance teams to:
- Understand the real operational condition of the WTG (Wind Turbine Generator)
- Manage anomalies before they become alarms thus reducing downtime, extending asset life and improving asset performance.
- Schedule WTG maintenance based on actual asset condition as opposed to scheduled and reactive maintenance.
Design Considerations
- We are looking for a simple, easy-to-use, Informative, modern design.
- Try not to have too much information on your dashboard, you can make them compelling by making the visualization interactive and enable users to walk through or drill into the different insights.
- Use color, visual comparison, and drill-down charts to highlight comparison.
- Have your designs of size: 1366 x 768px (Desktop only, Power BI is responsive by nature so just need to design/ build once)
Power BI Requirements:
- All principles of good UX design e.g. minimize user clicks, make the experience more intuitive, minimal time to reach desired selection criteria, and performance, good color, and font themes etc., these are all critical success factors for this challenge.
- Needs to follow Power BI Design Best Practices and also take a look at the Design Tips
- Please do some research on the Power BI software and get familiar with its purpose, limitations, and what's possible.
Required Dashboard Designs
1. Condition Monitoring Dashboard:
The Condition of the Asset / Component will be at its best when it is new but gradually deteriorates with age, operating conditions, weather conditions, Load etc. Hence it is important to know the speed at which the component is deteriorating and the factors responsible for the same. This dashboard will allow the user to monitor the asset health condition for key non-structural components.
The condition monitoring results are to be displayed in the form of dashboards. The dashboard visualization will be done at these hierarchical levels
- “Fleet > Model > Site > Turbine > System > Component > Subcomponent wise
(we have shared an image to show this structure and also we have shared the possible screens at each level - it is just for reference, we are looking for better UI/UX and also make sure it is compatible with Power BI)
NOTE: User should be able to drill-down or up the hierarchy, please see the additional info document provided in challenge assets in forums!
- At each level, the dashboard should show the estimate for the remaining life for the component.
- Each component will have a score that will indicate the “component condition” beyond which the component may fail.
- Display the status with a dot for each component. Dot essentially displays the condition of the component in the Red, Yellow and Green.
- If there is a condition-deterioration pattern, then we will need to show alerts to the maintenance personnel for corrective action to prevent the failures. Once the corrective action is taken, the dashboard should reflect the updated condition score and risk scores.
- Show heat map visualization showcasing results of asset health condition scores.
- Predicting probable cause (RCA - Root Cause Analysis) for yellow and red condition and propose action if any - Systematic Approach to understand what caused the Machine to Fail.
- Think through on what filters, the search would need to be put up!
- Provide an option to download, export the report.
~
Fleet Level: In this level, we show the list of fleets and with a number of turbines with condition status for the selected fleet.
Site Level: In this level, we show the list of sites and also the number of turbines in green. Yellow and red status"
Turbine Level: In this level, we show the list of turbines in that particular site with “Condition Score, Probability of Failure and Remaining Useful life”
System Level: In this level, we show the list of systems in that particular turbine with “Condition Score, Probability of Failure and Remaining Useful life” along with the number of components in various status (green. Yellow and red)
Component Level: In this level, we show the list of Components in that particular system with “Condition Score, Probability of Failure and Remaining Useful life and RCA (this shows the probable cause for this condition)”
Sub-Component Level: In this level, we show the list of Components in that particular system with “Condition Score, Probability of Failure and Remaining Useful life and RCA (this shows the probable cause for this condition)”
2. Anomaly Detection:
Anomaly is defined as any deviation from the reference. Components tend to show anomalous behavior due to various factors like the deterioration of the health, Load, wear and tear etc. It is important to analyze the anomalous behavior and the route cause for the anomaly. Once the route cause is known then corrective actions can be carried out to avoid failures.
Anomaly Detection will be done at the component and subcomponent Level, please see 09 Output Calculation.png to understand in which level it is calculated.
(We have shared the possible screens at each level - it is just for reference, we are looking for better UI/UX and also make sure it is compatible with Power BI)
- Develop a model to identify the anomalies at the component level and subcomponent level by comparing the real time performance parameter values with the optimum operating values discovered from the historical SCADA data.
- Model should detect the performance deviation from current operating values with that of the reference parameters.
- Model should be able to provide root cause analysis for the deviation from the established threshold. By identifying the anomalous point in the parameter, one can identify the root cause for the anomaly.
- Develop and display the performance deviation in operating parameter values in the form of a graph for each component for historical SCADA data..
- Predicting probable cause (RCA) for the Anomaly and propose action if any.
- Think through on what filters, the search would need to be put up!
- Provide an option to download, export the report.
~
Important:
- Keep things consistent. This means all graphics styles should work together.
- All of the graphics should have a similar feel and general aesthetic appearance.
- Focus on User Experience / how the user interacts within the dashboard.
Reference
Example dashboards design reference for your considerations:
- https://community.powerbi.com/t5/Data-Stories-Gallery/bd-p/DataStoriesGallery
- https://docs.microsoft.com/en-us/power-bi/service-dashboard-create
- https://id.pinterest.com/steffuhnee/power-bi-dashboards/?lp=true
- https://dribbble.com/powerbidesign
MarvelApp Prototype
- We need you to upload your screens to the Marvel App
- Please send your Marvel app request to csystic@gmail.com (challenge copilot)
- You MUST include your Marvel app URL in notes /comments while uploading (in your marvelapp prototype, click on share and then copy the link & share it within your notes while you upload).
Target Audience
- Operations and Maintenance Team
Judging Criteria
- How well you plan the user experience and capture your ideas visually.
- Cleanliness of your graphics and design.
- Overall design, UI and user experience.
- Consistency across the UX/UI
Submission & Source Files
Preview Image
Please create your preview image as one (1) 1024x1024px JPG or PNG file in RGB color mode at 72dpi and place a screenshot of your submission within it.
Submission File
- Submit JPG/PNG for your submission files
- Submit Marvelapp as part of your submission.
Source Files
All original source files of the submitted design. Files should be created in Adobe Photoshop, Illustrator, XD, or Sketch!
Final Fixes
As part of the final fixes phase, you may be asked to modify your graphics (sizes or colors) or modify overall colors. We may ask you to update your design or graphics based on checkpoint feedback.
Please read the challenge specification carefully and watch the forums for any questions or feedback concerning this challenge. It is important that you monitor any updates provided by the client or Studio Admins in the forums. Please post any questions you might have for the client in the forums.