Large volumes of measurement data can be time-consuming to comb through in order to find meaningful events during the drive cycle. Often these drive cycles result in gigabytes (GB) to terabytes (TB) of data being stored on companies’ shared storage drive or Data Lake. Engineers then utilize internal toolchains that serve a single purpose along with a steep learning curve to generate reports. These types of evaluations are very time consuming and prone to error.
Every technology company has an obsession with analytics, and for a very good reason. Data drives the business forward. Every industry is currently swooning over new technological evolutions such as machine learning, artificial intelligence, big data, and automation. All of these technologies are pushing our world to grow faster than ever, and in the process are creating increasing amounts of data. Many business leaders have decided to invest in data, whether it is data analytics, deep learning, data mining, business intelligence, or predictive modeling.
Capturing all data
In the automotive industry, Original Equipment Manufacturers (OEMs) have been moving away from traditional methods of developing vehicles. As Electric Vehicles (EVs) are increasingly becoming the next hot item in the global transportation market as well as autonomous driving with onboard computer vision, data analytics has become more in demand than ever. ETAS is helping the industry move towards a bigger goal – capturing all data. This new approach of capturing as much data as possible is gaining momentum with many OEMs and technology providers due to the rapid speed of technology development and “not knowing what we don’t know.” With ETAS’ high-performance drive recorders, we help OEMs capture as much data as possible during the vehicle development phase.
Analyze large data volumes in an organized way
The ETAS Enterprise Data Analytics Toolbox (EATB) was created to help organizations solve real-world problems and bring value and meaningful insights by analyzing large volumes of measurement data. From the vehicle calibration engineer’s perspective, EATB can reduce the time to pinpoint problematic issues, bridge the gap between engineers, and help end-users to complete the investigations and validation with predefined criteria and/or performance specifications. From managers to stakeholders, EATB can help end-users manage project progress and monitor any unexpected issues when they occur via the tool’s traffic light report system. EATB’s configuration reusability can enable knowledge sharing and reduce the time consumed to start a project from scratch. EATB is MATLAB based at its core; it provides maximum flexibility to help end-users turn valuable test data into actionable insights.
The EATB can consume a large number of measurement files and it is compatible with MATLAB based configuration files. The MATLAB language is very well known in the automotive engineering sector and is widely used for evaluation purposes. As a result, EATB produces beautiful yet interactive analysis reports based on user pre-defined configurations, including the support of drilling-down of data points. With traffic light report system, engineers can quickly pinpoint the issue and understand what matters the most at a glance. EATB takes hundreds of attributes and signals from the measurement data and provides an intuitive dashboard that allows users to slice and dice the data however they see fit – that flexibility, and the ability to drill down the data, is very empowering. We believe in enabling the user to reach as far as possible, and part of this vision is to provide tools to help end-users create stunning visualizations that represent their valuable data.
We hope our customers can use the Enterprise Data Analytics Toolbox to not only solve day-to-day common problems, but also to solve unexpected problems, and make their life simpler and easier.
If you would like to run a proof-of-concept with us, want to see a demo, or would like more general information, please contact me at Jerry.Chen@etas.com with any questions.