Drivetech - Blog #Analysis

Intelligent Reporting with StellarAi

Sat, 16 Dec 2023 16:08:34 +0530

Data analysis often falls short of its intended value unless it's documented in a report. Traditionally, the process of analyzing data and preparing a report involves separate, time-consuming activities. Engineers find themselves toggling between different software platforms—one for data analysis and another for documentation. Much of the reporting process involves manual handling of data analysis graphs and calculations to draft the report. Unfortunately, once created, reports often gather dust and aren't revisited, despite containing valuable insights on encountered problems, adopted solutions, and individual / team contributions.

At DriveTech, we recognize the need for a more efficient way to prepare reports, and that's where StellarAi, our data analytics platform, steps in. StellarAi comes equipped with a built-in reporting module that automates the bulk of manual reporting activities. This means engineers can now prepare reports within the same platform where they analyze their test data. With just a single click, the visualizations, calculations, statistics and observations generated in StellarAi can be seamlessly added to a report. Other Engineers having access only need to provide comments on various report items, making it as straightforward as filling out a web form. StellarAi takes care of the formatting, alignment, labeling, and indexing automatically, eliminating the need for manual intervention.

StellarAi goes beyond basic reporting by allowing users to partially analyze the data even within the report environment. Collaboration is made easy, as users can share their reports with team members for feedback and approvals. The real game-changer is StellarAi's automation of report generation for repetitive tests and analyses. Users can configure reports to be generated with a single trigger, whether based on time, file availability, or manual clicks. For instance, reports can be pre-generated as soon as a specific set of files is available to StellarAi.

To keep users in the loop, StellarAi sends email notifications for any report updates—whether a new auto-generated report is available, comments are added, or approvals are given. Reports can be downloaded in various document formats (.doc(x), .ppt(x), .pdf), and StellarAi tags each report with a word cloud of keywords and project parameters, ensuring easy retrieval and organization in its secure reports archive.

Just like test data, StellarAi consolidates and organizes your reports, providing an end-to-end solution for testing engineers. It addresses the final requirements of the data analytics process chain, making the entire process more efficient and user-friendly.

Effective Collaborations and Faster Decisions with StellarAi

Sat, 09 Dec 2023 18:39:54 +0530

In the present scenario of Automotive Test Data Analytics, a wide variety of software platforms are available that help Users perform the various processes required to analyze their Data. Solutions are available for a range of use cases and problem statements. However, one functionality which still remains unaddressed, is the ability to effectively collaborate with your team while working on the test data. Users generally end up using multiple different software to generate analysis, and conventional channels such as email, shared drives and chats to communicate their findings with their colleagues and concerned approving authorities. Anyone who has been through this knows that it is a time-consuming and inefficient way to collaborate. Naturally, at DriveTech, we decided to change this.

DriveTech’s Data Analytics platform StellarAi is built with ‘Collaboration’ at its core; along with ‘Data Consolidation’ and ‘Automation’. Data Analysis done in StellarAi is segregated in individual Projects. All team members working on a Project would be assigned the said Project in StellarAi. The Test Data collected from various sources under a project is accessible to all the people working on it. Further, in StellarAi Users are able to work in two environments – a private space where they can generate analysis by processing the shared files, and a common environment shared with fellow project team. This common environment is known as Dashboard. A collaborative space where Users can share their work with their peers and colleagues and get their feedback on it. Concerned team leaders can also record their approval / dis-approval of the analysis shared by any User.

Such functionality eliminates the need to spend time in manually handling and sharing data / analysis. Collaboration, however, is not limited to Dashboards and extends to Report generation as well. Once a data analysis (chart / calculation / statistic) posted on the Dashboard is approved, it can be directly added to a ‘Report’ in a couple of clicks. StellarAi’s Report generation environment allows Users to add comments / observations to a graph or calculation – akin to filling out a webform; without the need to spend time in formatting the document. Once a User has completed a report, they can invite others to review and approve the same, similar to sharing a text / spreadsheet document with your colleagues online. This ensures that the final area of collaboration is addressed as well. Once the report is approved, Users can publish and download the same (in PPT / PDF / Word formats) for offline record keeping.

Through its built-in collaboration functionalities, StellarAi saves significant amounts of time required for data handling, by facilitating effective team work and thereby faster decisions. StellarAi also brings all data analysis processes under one roof – providing an end-to-end solution for all automotive test data analytics requirements.

Integrating Test Management and Data Analytics for Automotive Testing

Fri, 24 Nov 2023 18:36:41 +0530

Introduction:

In the ever-evolving landscape of automotive development, engineers often grapple with numerous challenges, from analyzing test data to managing resources and ensuring seamless inter-departmental coordination. These hurdles can result in delays during the vehicle development cycle.

DriveTech, recognizing these pain points, offers a comprehensive solution – the 'Test Management Suite' (TMS). The TMS is a versatile cross-platform solution tailored to suit the unique structure and workflow of each organization. It seamlessly deploys on iOS, Android, and existing systems, fitting into any stage of the workflow. TMS is essentially a highly customizable platform that organizations can use to bring their test management online, in a very short amount of time.

TMS simplifies test scheduling, resource allocation, rig and operator management, lab announcements, notifications, downtime tracking, and daily dashboards. However, the true standout feature of TMS is its integration with DriveTech's data analytics platform, StellarAi. StellarAi revolutionizes testing by automating both the testing process and post-processing of test data. The StellarAi + TMS combination centralizes test data, allowing it to be merged, searched for specific events, and leveraged for automated data analysis. It also offers centralized DBC management, Message to Signal conversions, and benchmarking.

Collaboration is essential in any test program. StellarAi facilitates seamless & secure data sharing among concerned team members, ensuring that users can collaborate efficiently while maintaining the confidentiality of sensitive test data. The platform also streamlines report generation, automating many manual processes. With StellarAi, users can generate professional reports with just a few clicks. The solution is particularly well-suited for repetitive data analysis tasks, offering pre-built Analytical Templates that simplify report generation. Additionally, StellarAi can integrate with test benches to automatically fetch data after each test.

Conclusion:

The TMS + StellarAi solution empowers users to achieve efficient test management, resource allocation (both human and machine), test data consolidation, automated data analysis, collaboration, and automated report generation. TMS + StellarAi brings a wealth of value-added features, making it an indispensable tool in the automotive testing industry. To explore these features further, visit the link below.

Streamlining Network Analysis with StellarAi

Fri, 24 Nov 2023 18:36:41 +0530

Introduction:

Analysis and managing of post recorded CAN / CAN-FD message logs isn't everyone's cup of tea and requires skilled professionals. CAN / CAN-FD Log Analysis, whether at the ECU development level or the prototype vehicle level, involves delving into ECU architecture, testing, and validation. Still, most of the engineers are only able to do the analysis once the message files are converted into signal files. Currently, in the automotive market the analysis can be done only on single files, or you must concatenate all the files into one and then do the analysis of that file using special scripting. The time consumed in all these activities is too long and hence the solution to the problem is delayed. This also depends on how your PC is set up to run different software. At the end it is the OEM who suffers.

Solution:

Recognizing the need for a more efficient approach, we turned to our in-house Data Analytics platform, StellarAi. StellarAi empowers users to assess data quality before embarking on their analysis. It also promptly notifies users of any data loss within a file, which may occur due to bus or network issues. Upon uploading the file into the database, StellarAi conducts a quality check, enabling users to have confidence in their data before commencing analysis. Users can gain insights into channel-specific statistics, including message counts, unique IDs, and bus utilization. Further, StellarAi notifies the user regarding the various message types found in the file, such as Diagnostic messages, Negative responses, error frames, response and transmit messages.

Once the user has a comprehensive understanding of their data, they are better equipped to initiate their analysis, ultimately saving time and enabling them to determine where to commence or whether to discard certain data entirely. Interestingly, StellarAi allows users to manage several messages at once and do complex searches to identify particular criteria in a variety of files. Message to Signal conversion is also managed seamlessly with StellarAi. The Data Base Container Management function allows for centralized management of DBCs and allows conversion of messages into signals using the DBC(s), allowing for further analysis of the data.

Conclusion:

The range of value-added features built into StellarAi offer an end-to-end solution to the Users for CAN / CAN-FD Data Analysis as well as other kinds of automotive test data analytics. The precise nature of the solution resolves the actual pain-points faced by the User; saving time and improving efficiency.

Centralized DBC Management

Fri, 24 Nov 2023 18:36:41 +0530

The contemporary landscape of software-defined vehicles has given rise to increasingly complex vehicle E/E architectures. Such an environment makes it critical to ensure that the database container (DBC) files for each architecture are managed, made accessible and also safeguarded at the same time. The DBC files are the IP of the OEM and need to be secured. However, it is also necessary that the concerned teams within the OEM’s organization and their industry partners are able to access the DBCs and use them effectively to interpret network message files. In short, it is necessary to ensure the following:

Systematic management of DBCs (.dbc / .arxml).
Centralized control on the release / withdrawal of DBCs from circulation within the organization.
Concerned user groups are able to effectively use the DBCs to interpret message files.
Proprietary information contained within the DBCs is secured and shared only on a need-to-know basis.

Solution:

Recognizing the importance of the above, DriveTech is proud to introduce for the First time in the IVN world, ‘Centralized DBC Management and Distribution’ with its data analytics platform, StellarAi.

Our approach involves consolidating DBC management within StellarAi, allowing only a single user or administrator to release or withdraw DBCs. This enables the OEM to notify User groups with the release of new DBCs, mapped with the E/E architectures relevant to them. OEMs can also withdraw obsolete DBCs from circulation, ensuring exclusive ownership.

The DBC Management feature allows StellarAi users to apply DBCs to message files and retrieve signal data from them. Users can also view channel-wise and file-wise DBC matching percentages along with other statistics, providing a comprehensive understanding of DBC suitability. This also ensures that users do not spend time working with the wrong DBCs.

Further, the most important aspect of the feature is that StellarAi allows the use of DBCs without allowing Users to view the information contained within the DBCs or allowing them to download the DBCs. This ensures that access to DBCs is secured and DBC files themselves are not circulated physically; maintaining the sanctity of the DBC contents and enhancing the safety of the OEM’s IP.

Conclusion:

DBC Management capabilities have been offered by StellarAi for the first time in the IVN domain and the feature has no parallels anywhere in the automotive test data analytics domain. Using this feature, OEMs can ensure systematic management and control of DBCs on-par with the contemporary software version control methods. DBC Management thus enables OEMs to have absolute control on their hard-earned IPs and safeguard their business interests.

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.