Drivetech - Blog #Large Signal DATA

Streamlined Vehicle Benchmarking with StellarAi

Sat, 02 Dec 2023 19:07:07 +0530

Benchmarking stands as a conventional practice in the automotive industry, serving as a vital tool for OEMs to discern how their products measure up against competitors and to gain critical insights on market dynamics. Traditionally, the evaluation of vehicles leaned heavily on the mechanical aspects, but with the increasing software dependence of vehicles, the electronic and electrical (E/E) systems too have become important while benchmarking.

This, however, poses a different set of challenges for the OEM. Achieving a meaningful comparison requires the meticulous evaluation of two vehicles under identical test conditions—a process known for its inherent time-consuming and labor-intensive nature. Adding to the complexity, contemporary software platforms frequently lack dedicated benchmarking capabilities. This makes it difficult for test engineers to effectively analyze the performance of their proto. Vehicles against benchmarking vehicles.

DriveTech’s in-house data analytics platform, StellarAi provides an integrated ‘Compare’ feature that addresses the above challenges. This feature serves as a catalyst for engineers, enabling them to conduct efficient comparisons of parameters between the prototype vehicle and its corresponding benchmarks.

Users benefit from the ability to overlay and slide parameter curves, effectively eliminating irrelevant data and facilitating the simultaneous comparison of multiple parameter sets. Further, StellarAi is the only platform that allows Users to merge and compare data from multiple test files for both the proto vehicle and benchmark vehicle(s). Users can choose to visualize parameters with either a pair of single ‘Multiple Y-axis' plots or multiple pairs of ‘Single Y-axis' plots. An additional noteworthy capability of StellarAi is its capacity to accommodate the comparison of data from up to four vehicles concurrently.

The above functionality, combined with its standard automation capabilities, makes StellarAi the most suitable platform for analysis of benchmarking data. Its ‘Merge & Plot’ functionality allows for huge datasets to be combined and compared; whereas the ‘Automation’ feature helps users auto-generate comparison visualization from live tests.

Example Use case: Let's take the case of two vehicles equipped with IVN Data Loggers, being driven in an identical manner on a test track or on a dyno, for a duration of 12 hours. The Data Loggers would generate multiple files as they capture the vehicle performance. These data files can be fetched by StellarAi while the test is progress and used to automatically generate a pseudo-real-time comparison between the two vehicles.

The significance of the 'Compare' feature lies in its ability to facilitate an apples-to-apples comparison of vehicles, with due consideration the prevailing test conditions. This streamlined benchmarking process not only translates to significant time savings but also helps in significantly enhancing the accuracy of the analysis.

In conclusion, DriveTech's StellarAi not only effectively addresses the pre-existing challenges in benchmarking electronic systems but also serves to streamline the entire process. This not only translates to a considerable saving of time but, more importantly, it elevates the precision and robustness of performance analysis. The innovative 'Compare' feature emerges as a beacon in simplifying benchmarking analysis. With its user-friendly interface and efficiency-driven design, StellarAi establishes itself as a pivotal tool that promises to propel OEMs toward sustained success and advancement in this dynamic sector.

How StellarAi's Advanced 'Event-based Search' helped an OEM locate a crucial problem from their big data.

Sat, 04 Nov 2023 13:41:00 +0530

The Problem
While working closely with one of our OEM customers, DriveTech was tasked diagnosing a critical issue they were facing with their proto vehicle fleet. Essentially the requirement was to collect network data from affected vehicles, analyze it and come up with the correct diagnosis in a week.

The Solution

DriveTech installed data logger devices and recorded the CAN network data from the vehicles and their multiple networks. This data acquisition was done for a week in hope to catch a replication of the failure event on the CAN log. During this time the vehicles were routinely driven for 100 to 150 kms every day, generating large amounts of data. The devices captured multiple failure events, and now the data had to be analyzed. This case was very critical and demanded urgent resolution as the failure was adversely affecting the test program. DriveTech was left with ~ 100+ GBs of data (500+ files) which had to be analyzed. Each file would take around 45 minutes for analysis and analyzing 500+ files would mean spending a month or more just isolating the events.

The Turning Point
To specifically address this, we decided to leverage our in-house Data Analytics platform, StellarAi. This platform excels at handling vast amounts of data with minimal processing time. The standout feature that proved invaluable in this case was the Advanced ‘Event-based’ Search functionality. We were looking for specific events within this huge amount of CAN data, and the advanced event-based search needed only a 1-line query to locate the files containing failure events in less than a minute.

We were able to quickly visualize the data from these files, which helped us pinpoint the precise instance when failure occurred. We were able to visualize multiple such files simultaneously which helped us narrow down the potential causes.

Collective analysis of files from all the affected vehicles enabled us to precisely identify the cause of failure and come up with a diagnosis. We were also able to recreate the failure on a bench set up, validating our diagnosis.

Conclusion 

After some more on-road testing & inspection, we were able to definitively conclude the reason for failure and notified the Automaker with potential insights. DriveTech was able to use StellarAi’s value added features and converge the analysis quickly. Without features such as event based Advanced Search it would have taken anyone a very long time to resolve the issue; while losing valuable time in getting new models into the market.

Merge and Plot Billions of Data Points; On-the-Fly, No Pre-processing

Fri, 20 Oct 2023 17:29:40 +0530

Introduction:

DriveTech was recently working on client project which involved Durability testing for a fleet of vehicles. It generated huge amounts of data on a daily basis, and at the end of each day it was expected to have an incremental and a cumulative analysis of the data till date.

The Client was essentially facing the following four challenges:

- Merging multiple signal files together.

- Prevent loss of data due to sampling.

- Prevent data duplication (caused by sampling and re-sampling of the original data).

- Sharing of files / data analysis with team members.

For this, DriveTech developed a solution that can perform all the above and more.

Our Research:

DriveTech collaborated with the Client’s teams to get a deeper understanding of the issues faced. The Client teams were running a sequence of road tests on one of their proto vehicles and were recording CAN data on the same. We noted that this was leading to generation of a lot of data files from each test. The testing team wanted to analyze all the files as a single data set. They converted the message files to signal files and tried to manually combine multiple files together. However, we discovered that this was leading their system to crash. This meant that they had to analyze each file individually. Further they were sampling the files at a standard sampling interval. We understood that whenever a different sampling interval was needed, new re-sampled files had to be painstakingly created causing duplication of data, increasing storage requirements, as also adding the time required for re-sampling the data.

To quantify this, on average, each 8-hour drive test generated ~ 20 signal files, each of size ~ 150 mb. Analyzing each file will require at least 1 man-hour. This means that analyzing 20 files would take 20 man-hours i.e., 2 to 3 working days; making individual file analysis laborious and impractical.

The Solution:

To cater to the requirements, DriveTech introduced a new feature to its automotive test data analytics platform – StellarAi; called ‘Dynamic Sampling’ (DS). Dynamic Sampling allowed users to visualize a group of files together as a single dataset. StellarAi slices the original consolidated data set to isolate the parameters to be visualized, and the time period of interest. This eliminates the need to handle the entire data set and reduces StellarAi's own computing requirements.

Dynamic Sampling helps StellarAi to intelligently set a fixed sampling interval, optimized based on the available data bandwidth and rendering muscle of the User's workstation. Users can visualize a signal parameter across the entire data set based on the fixed sampling interval. DS also enables Users to drill-down into a particular slice of the graph, as seen here below.

As the User drills down, Dynamic Sampling adjusts the view to display just that selected data window, freeing up computing resources, and effectively crop the data under study, to allow for lower sampling interval within the selected data window.

The result is an enhanced user experience where individuals can continue drilling down into specific events within the data. This means users can even reach a point where they are viewing the actual, non-sampled data. The DS approach also ensures that all users can view comprehensive overviews of massive amounts of data; reliably rendered in a deterministic period of time.

StellarAi equipped with DS, eliminated the need for manual sampling, keeping the original data intact and readily accessible. This also ensured no data duplication, no data loss due to sampling, and the ability to adjust the sampling interval on the fly to meet the User’s analytical needs.

Further, because of StellarAi’s centralized ‘Data Repository’ and its existing collaboration environment, Users were able to share data analysis with their colleagues and effectively collaborate with each other without having to physically share large amounts of data.

Conclusion:

Due to the modular architecture of StellarAi, DriveTech was able to quickly roll out the Dynamic Sampling, a new feature that effectively addressed Client’s challenges. It ensured that the Client is able to:

- Analyze multiple files together.

- Avoid manually sample / preprocess the data.

- Eliminate data duplication.

- Share their work with their colleagues easily.