MOTOR Magazine

A MOTOR Magazine Newsletter
July 23, 2019

Contributed by Bob Chabot
Predictive Diagnostics Gain Support

What do service professionals need to know now?

Vehicle predictive diagnostics is on the verge of changing how vehicles are maintained. This has been talked about for some years, and some minor applications have even been initiated, such as General Motors OnStar’s proactive alerts. But until now, most in the automotive maintenance and repair industry have paid little attention. That’s about to change.

The Society of Automotive Engineers (SAE), International Organization for Standardization (ISO), automakers, Robert Bosch GmbH and other organizations are now actively addressing and building the standards needed to drive prognostics forward. If you aren’t already doing so, paying attention what SAE or others are doing will help you prepare for the near future of automotive repair and service.

“Predicting a likely future failure in vehicle components and systems in advance of the occurrence is important today, and will be even more critical for autonomous vehicles, perhaps far from their home bases,” advised MOTOR contributor Paul Weissler, in a presentation to SAE. He shared much of the progress toward predictive diagnostics being made by SAE’s Industry Technology Consortia (ITC) via its Recommended Practice JA 6268 Document. Shown in the cover image, SAE JA6268 formally describes the evolution of diagnosis and prognostics in vehicles.

Despite numerous advantages that predictive analytics brings, it is essential to understand that forecasting is just an estimate, the accuracy of which highly depends on data quality and stability of the situation, so it requires careful treatment and continuous optimization. That’s why the involvement of SAE and other reputable organizations is essential. In short, predictive analytics tells what is likely to happen to a vehicle in the near future. It uses the findings of descriptive and diagnostic analytics to detect tendencies, clusters and exceptions, and to predict future trends, which makes it a valuable tool for forecasting needed repairs before failure. (Image — Society of Automotive Engineers)

Will Reactive Maintenance Be Replaced By Predictive Maintenance?
“Adapted from aerospace, where the safety aspects are obvious, the objective of prognostics is to change motor vehicle care and repair from mileage-and-time based intervals for maintenance to one using analysis of real-time data,” Weissler notes.

Look at the concept this way: As much as feasible, diagnosis of failures after they occur would be replaced by predicting a likely future failure in a “sweet spot” as close to two weeks in advance as possible. In other words, this prognostic “prediction” is intended to detect and address an impending failure while the performance still is seemingly within a normal range. In addition, the advent of automated driving and connected vehicle technologies is also fueling interest in prognostic-based service and repair.

“The aim of prognostics care and repair is to derive maximum life from components and systems without subjecting the user to loss of safe use at inconvenient times, compared with the economic disadvantage of service replacements at unnecessarily short intervals,” he explained. “Currently, most automobile diagnosis is performed by a technician, using service information (manuals and/or on-line resources), test equipment and shop tools. Any needed software updates are made at the technician’s shop, using an internet connection with an SAE J2534 pass-thru device or an OEM tool. Only a few cars are able to use telematics to perform ‘over-the-air’ software updates.”

Robert Bosch GmbH’s vision for predictive diagnostics is shown above. Bosch says that prognostics will: (1) Facilitate vehicle-specific prediction of the component and system condition; (2) Optimize planning of maintenance tasks based on status data from the connected vehicle; (3) Reduce the time required for repairs by up to 25 percent through improved workshop utilization and optimized spare parts logistics; and (4) Enable some repairs to be facilitated with an over-the-air repair rather than an actual shop visit. (Image — Robert Bosch GmbH)

Creating a Continual Data Stream is an Essential Step
Weissler explains that determining when an automotive component, obviously designed for long life, is close to failure means there must be continuously available data on its health. He cited as an example General Motor’s OnStar, which introduced automotive prognostics on a range of 2016 Chevrolet models with OnStar 4G connectivity, which covers key parts of engine starting and operation including the battery, starter and fuel pump.

“Some components age gracefully,” Weissler notes. ”That is, they deteriorate on a known curve, and lend themselves readily to prognosis. Those with key component lives that presently are less predictable would benefit more from real-time health assessment, perhaps enhanced by machine learning or other assistance. Their health assessment has to be built into components and systems. The automotive industry is looking to the SAE’s ITC to create the framework for this.”

He added that last year, SAE’s ITC released JA 6268, an aerospace and automotive Recommended Practice (RP), titled Design and Run-Time Information Exchange for Health-Ready Components. Think of a health-ready component as a supplier-delivered part or sub-system that is enhanced, perhaps with additional sensors, to report on its health, and/or provide the integration information so that components and/or an entire on-vehicle system can be covered.

“The first JA 6268 level (known at SAE as Level 3) is at the component level, and the ITC is seeking to build a registry,” Weissler explained. “Initially, the registry includes the component identification, and the supplier, plus the validation approach (i.e. its design-time and/or run-time information), format of the health-ready information (math model or math relationship in machine-readable format), name of OEM or integrator and also, the dates of compliance. This registry is the SAE ITC’s spin-off to begin the development of Health Ready Components and Systems (HRCS).”

The aim of predictive diagnostics is to derive maximum life from components and systems without subjecting the user to loss of safe use at inconvenient times, compared with the economic disadvantage of service replacements at unnecessarily short intervals. SAE says it will be a crucial need with the advent of automated driving. (Image — Society of Automotive Engineers)

Integrating Sensors into Prognostic Maintenance
“The registry is intended to lead to Integrated Vehicle Health Management (IVHM) and primarily for autonomous vehicles, eventually to Self-Adaptive Health Management (SAHM), explained Steven Holland, a consultant who helped GM deploy the company’s prognostics initiative while he was employed there.

Weissler noted that Holland shared some of the difficulties both at the diagnostic level and also in prognostics. These included No Trouble Found (NTF) and No Fault Found (NFF) rates, which may exceed 50 percent, or even up to greater than 90 percent.

“Perhaps Not My Fault (NMF) may seem like a better name at first,” Holland humorously suggested. “But there as some serious reasons for NTF that need to be addressed by the registry.” These include:

  • The test method doesn’t log all failure modes. This often was identified as the issue when replacement of an electronic module that didn’t log a code or have any other adverse sign, but actually was found to have fixed the problem.
  • The test environment is unrepresentative of when the failure occurred (temperature, pressure, humidity, vibration, etc.)
  • There are wiring/connection issues not identifiable by the test procedure.
  • Other modules, which should be cooperating in the circuit/system, are not performing as expected.
  • A key specification for the component was waived as a cost-saving decision.
  • Maybe there really is nothing wrong with the component.

“The objective of the registry is to enable participants to know the process is consistent with the RP and was verified,” Holland observed. “A registry of known suppliers also enables sharing of costs and some leveraging of knowledge.”

Technicians are aware of most forms of data. Some have recently begun to hear of Predictive Data, but few have heard of the next form of data known as Prescriptive Data. While all types of analytics ultimately support better decision-making, prescriptive analytics outputs a decision rather than a report, statistic, probability or estimate of future outcomes. (Image — Gartner Inc.)

“Sensors incorporating health assessment would be integrated in an IVHM architecture based on the International Organization for Standardization’s (ISO’s) Standard Document 13374,” added Weissler. “These sensors include capabilities for data acquisition, manipulation, measurements of state and health, along with a prognosis if indicated and generation of an advisory if needed."

“Failure mode classification also is part of the assessment strategy, led by cost-per-vehicle for repairing a predicted failure,” he concluded. “Next in the picture is the severity, led by Most Severe (e.g. Vehicle non-operational or there is a safety issue), followed by Urgent, Important (e.g. Including customer inconvenience factor), then Minor Repair and finally Least Severe (e.g. Goes into routine maintenance).

Expect more changes to come, which will impact you and the way vehicles are serviced.

Important Links
MOTOR Current Issue
MOTOR Current Issue
MOTOR Magazine

MOTOR Information Systems • 1301 W. Long Lake Road, Suite 300 • Troy, MI 48098