ASQ RRD Series: Big Data Analytics – Telematics Data Analysis by Dennis Craggs
Thu, Nov 8, 2018 12:00 PM – 1:00 PM EST
Engineers conduct tests to verify that product meet engineering standards.
These standards were developed with customer surveys, duplication past standards, or relying on expert opinions.
Modern technology provides a new tool to validate standards by measuring product usage by the customer.
An automotive example will be discussed, but the methods have much broader application.
Automobile companies installed telematics modules on fleet vehicles, with the consent of the owner, to collect and store usage and environmental data.
The volume of data was enormous.
Different analytic methods were required for different data types but there were only a few data types to consider.
The raw data needed to be standardized for different vehicle miles or time.
Then counting data, like trips/day, were analyzed with simple probability distributions.
State data, like switch setting, need to be analyzed for transitions and time duration in states.
Continuous measurements are more difficult.
Engineers frequently use bar histograms, but bar histograms quickly become unreadable when two or more data sets were combined in the same graphic.
Methods were developed that allowed many histograms to be analyzed fleet usage patterns and develop the 5th, 50th, and 95th customer percentiles.
The standards can then be validated using the customer data.
Dennis Craggs attended the University of Detroit and Wayne Statue University achieving Masters in Engineering Mechanics and Operations Research, is a licensed Professional Engineer, and is a Quality and Reliability Engineer.
In the Aerospace, he worked at NASA and Teledyne CAE, and in Automotive, Ford and Chrysler.
He applied the disciplines of fluid mechanics, heat transfer, mechanical and electrical design, testing, and development.
He learned several programming languages and develop significant software.
As a statistician, he assisted managers and engineers in the development, review, and approval of validation standards, analyzed warranty and test data, and developed methods to statistically analyze vehicle lifetime usage.
He was member of a joint USA SAE and German ZVEI taskforce that developed SAE-J1879 “Handbook for Robustness Validation of Semiconductor Devices in Automotive Applications” and helped to develop the automotive lead-free electronic validation standard USCAR40, “Lead Free Solder Validation Test Plan”.
He taught graduate level statistics and reliability at Wayne State University, and as independent trainer presented “An Introduction to Minitab” seminars to corporate clients.
Dennis presented at the Society of Automotive Engineers, the American Society for Quality, the Automotive Electronics Council, and ISSAT conferences, and published SAE and ISSAT technical papers.