Содержание
- 2. Project Summary Explanation of the Brake Model Nissan’s Data Set Summary of existing dataset Applying Pitstop
- 3. Brake model is working xxx xxx Comparison to mileage based shows a distinct advantage xxx xxx
- 4. TL;DR the existing dataset can be used for a brake model Secret Sauce: Combining telematics, service
- 5. Detect when braking events occur. Calculating a metric of brake usage per vehicle - energy dissipation
- 6. The data has good attributes for Brake Predictions High resolution data from a small volume of
- 7. High resolution data from a small volume of vehicles (Engineering test fleet) Trip data does not
- 8. Applying the brake model - exploration on FET data Expectation is satisfied with engineering test fleet
- 9. Front Left Inner Front left Outer Front Right Inner Front Right Outer Rear Left Inner Rear
- 10. The brake model is showing Success & validation Showcase accuracies and strong signs of success with
- 11. Next steps to further prove out the brake model High resolution data helps create accurate dissipation
- 12. Steps to validate the model Step 1: calculate the dissipation for each vehicle and assign it
- 13. Validate the model Step 3: Comparison between each cohort (blue dotted line) and the average (orange
- 14. Alert would be early. This leads to customer trust issues. “ The dealer just wants me
- 15. Summary: Expected conclusion of phase 2 We expect phase 2 will prove that the brake model
- 16. Nissan Roadmap to Additional Predictions
- 17. Pitstop’s current Models How the Pitstop data engine works Current Pitstop Models / Data Requirements Custom
- 18. Time series sensor data Repair order data Pitstop insights
- 19. Existing Predictive Algorithms: Battery Failure Predictions Engine Timing/Combustion Failures Transmission failure predictions Emissions Analytics Diesel Engine
- 20. Battery Remove no start scenarios Reduce electrical failures Examples include: Battery, Alternator, Starters, Parasitic loads etc..
- 21. Recommendation to extract further value Underinflation & Leakage Load & Utilization Monitoring Pad Wear Insights Tread
- 22. Additional Algorithm Details Problem Delivery Van Sliding Door was not intended to open and close 100’s
- 23. The Nissan data has good attributes for models High resolution data from a small volume of
- 24. The dataset overall does have challenges & gaps The dataset consists of telematics generated and service
- 25. Recommendation to extract further value Start by asking what types of value propositions are most important
- 26. TL;DR the existing dataset can be used for a brake model From the existing list of
- 27. Steps required to track Brake Wear Detect when braking events occur. Calculating a metric of brake
- 28. Custom Algorithm Example Problem: Delivery Van Sliding Door was not intended to open and close 100’s
- 29. Start by asking what types of value propositions are most important to the market. For example
- 30. Start by asking what types of value propositions are most important to the market. For example
- 31. Recommendation to extract further value 67%
- 32. Start by asking what types of value propositions are most important to the market. For example
- 33. Start by asking what types of value propositions are most important to the market. For example
- 34. Recommendation to extract further value
- 35. Text
- 39. Скачать презентацию