Volkswagen + Google Cloud: Using Machine Learning to Drive Smarter with Energy Efficient Cars
2676
Of your peers have already read this article.
2:30 Minutes
The most insightful time you'll spend today!
Volkswagen strives to design beautiful, performant, and energy efficient vehicles. This entails an iterative process where designers go through many design drafts, evaluating each, integrating the feedback, and refining.
For example, a vehicle’s drag coefficient—its resistance to air—is one of the most important factors of energy efficiency. Thus, getting estimates of the drag coefficient for several designs helps the designers experiment and converge toward more energy-efficient solutions. The cheaper and faster this feedback loop is, the more it enables the designers.
Unfortunately, estimating drag coefficient is an expensive and time-consuming operation that involves either a physical wind tunnel or a computationally intensive simulation. This can be a bottleneck in the feedback cycle.
For this reason, Volkswagen and Google Cloud decided to collaborate on a joint research project to investigate using machine learning (ML) to get fast and inexpensive estimates of the drag coefficient. In this post, we’ll explore the challenges and approaches undertaken in this project.
The core principles of the project were simple. First, we needed to collect a dataset of existing car designs and their respective drag coefficients. Then, we needed to create a representation of the various cars that would be suitable for ML. The next step was to train a deep learning model to predict the drag coefficient, and then, finally, we would use that model to efficiently estimate drag for any new design.
Representing three-dimensional car designs
Design software recreates a physical object as a three-dimensional triangle mesh made up of three types of objects—faces, edges, and vertices. Figure 1, below, shows such a mesh for an Audi S6. Faces are flat surfaces, such as the window in a car door. An edge is where two faces meet (e.g., the side of the door), and a vertex is where two or more edges meet, such as the corner of the door.
Car bodies, however, come in all shapes and sizes. A Volkswagen Golf economy model is very different from a Tiguan SUV, and a single vehicle can have both large smooth surfaces as well as areas with delicately designed features. Consequently, there can be a huge variety from one polygonal mesh to the next.
ML models need consistent representation in order to form robust generalized rules. With such a dramatic variance between each polygonal mesh, the models would be compromised and the results could have huge margins of error.
We needed to find a way to create simple meshes that capture the shape of the car but are still suited for ML models.
Representing a car with digital shrink wrapping
Rather than building a representation of each car from the ground up, we applied a “shrink wrapping” method for the 3D meshes. The principle is very similar to vacuum-sealing a cucumber. The cucumber is placed in a plastic bag and the air is then gradually removed until the bag fits tightly around it, capturing its shape.
Our approach works similarly: we start with a base mesh, a simple shape that corresponds to the plastic bag, and we deform it until it captures the shape of the target mesh. For our purposes, the base mesh is a simplified representation of a car and the target mesh is the particular car we are designing for at that moment. Such meshes can be defined, managed, and presented to ML models for training using the Tensorflow Graphics and trimesh libraries.
Our “shrink wrapping” method mainly works by iteratively minimizing a measure of distance (e.g., chamfer distance) between the two meshes. Additionally we can regularize our mesh to preserve certain qualities, like smoothness, in the resulting mesh. This iterative optimization is analogous to the vacuum pump, gradually shrinking and fitting the vertices of the mesh as closely as possible to the complex shape of the car. With shrink-wrapping, we are able to produce cleaner meshes that are more suitable to our estimation task. An example of such a procedure is shown in Figure 2.
How to train a model
Shrink-wrapping the 3D car designs was an important first step, but the work was far from over. Our next challenge was to build and test the machine learning algorithms.
We wanted our algorithms to estimate the drag coefficient as accurately and quickly as possible each time it looked at a new design. To do so, we had to train the ML models on existing data.
From publicly available datasets, we calculated the drag coefficients for 800 different car meshes, which we trained the models on. Then, we evaluated the trained models on a further 100 meshes, seeing how accurate their estimates were on new data.
As we worked through this training, we refined our approach. Initially, we tested models based on convolutional neural networks – similar to PointNet – that observed only the vertices, i.e., the fixed points in each mesh. But when we tested mesh-convolutional models – similar to FeastNet – we found a slightly different focus improved the accuracy of the estimates. Rather than focusing on vertices alone, these models looked at a mesh of vertices and how they relate to each other. These models placed each vertex in a richer context, leading to more accurate estimates when air-flow hit particularly subtle design features.
Working in parallel and at scale
To collaborate across time zones and two organizations, we’ve used the Google Cloud Vertex AI platform.
Vertex AI Workbench serves as a central hub to interact with other services and infrastructure on the Vertex AI platform. It enables quick experiments and preparation of training packages for resource-intensive ML model training jobs, all in a Python notebook environment for immediate execution of code. The notebook environments allow code-based interaction with other services on Google Cloud and ML tools such as Vertex AI Training and Vertex AI Pipelines.
The process of training a new model is a seamless one. First, a dataset is prepared and stored in Google Cloud Storage, usually with the help of Tensorflow Datasets. Then, for every ML model we want to test, we package and store the training code as a container image with Google Cloud Build and Container Registry. This ensures that every job is fully documented, including the provided parameters, training code package, logs from the training task, and resulting artifacts such as metrics and model files.
From there, we submit the model to the Vertex AI Training service, which provides easy access to large scale infrastructure and hardware accelerators, such as GPUs and TPUs, by simply defining resource needs when submitting a job. By using Vertex AI Training’s hyperparameter tuning feature, we can run experiments in parallel with multiple neural networks to find the right one for our purposes.
With Vertex AI Tensorboard, we can capture metrics and visualize the results of our experiments. These are readily available to anyone in the team, wherever they are in the world, for a wider discussion.
The first milestone
This joint research effort between Volkswagen and Google has produced promising results with the help of the Vertex AI platform. In this first milestone, the team was able to successfully bring recent AI research results a step closer to practical application for car design. This first iteration of the algorithm can produce a drag coefficient estimate with an average error of just 4%, within a second.
An average error of 4%, while not quite as accurate as a physical wind tunnel test, can be used to narrow a large selection of design candidates to a small shortlist. And given how quickly the estimates appear, we have made a substantial improvement on the existing methods that take days or weeks. With the algorithm that we have developed, designers can run more efficiency tests, submit more candidates, and iterate towards richer, more effective designs in just a small fraction of the time previously required.
Going forward, faster and more accurate estimates could even enable more automated searching for efficient designs, which would help both engineers and designers to hone in on the areas of the vehicle body where they could have the most impact. An important next step will be integrating the results into 3D design software to let designers benefit from the output and provide feedback.
As we continue, our focus is on improving the accuracy of the models. Firstly, we will build a larger, better quality dataset. Secondly, we will improve our shrink-wrapping algorithm to capture more details. Finally, we will enhance our existing models by experimenting with Vertex AI Neural Architecture Search to explore and experiment with different neural architecture options.
Moreover, we believe that our results for drag coefficient estimation is only a starting point for further exploration. There could potentially be numerous use cases in the space of physical simulations and assessments where cost and time savings could be achieved through ML-based estimators.
Acknowledgements
This work wouldn’t have been possible without the contributions from Volkswagen Data:Lab, Google Research, and Google Cloud. Thanks to Ahmed Ayyad, Dr. Andrii Kleshchonok, Dr. Daniel Weimer, Gülce Cesur, Henrik Bohlke, Andreas Müller from Volkswagen, Ameesh Makadia, Ph.D., and Carlos Esteves, Ph.D., from Google Research, and Daniel Holgate, Holger Speh, and Dr. Michael Menzel from Google Cloud.
How Domino’s Increased Monthly Revenue By 6% with Google’s Analytical Tools
DOWNLOAD CASE STUDY3902
Of your peers have already downloaded this article
4:15 Minutes
The most insightful time you'll spend today!
Pizza purveyor Domino’s is dominating delivery sales around the world. Today, Domino’s is the most popular pizza delivery chain operating in the U.K., the Republic of Ireland, Germany, and Switzerland—and sales just keep growing.
In these regions in 2014, Domino’s sold 76 million pizzas and generated £766.6 million (1.02 billion USD) in revenue — a 14.6% increase from the previous year.
In the U.K. and Ireland, online sales are increasing 30% year over year and currently account for almost 70% of all sales. Notably, 44% of those online sales are now made via mobile devices.
Multi-Device Purchasing Means Fresh Opportunities
Domino’s is a consistent digital innovator. Much of the company’s success stems from early investments in ecommerce and mobile commerce platforms that help people easily purchase pizzas from different devices.
Domino’s sold its first pizza online in 1999. It then launched an iPhone app in 2010, quickly followed by apps for Android and iPad in 2011, and a Windows app in 2012. By late 2014, Domino’s customers could even order pizzas from Xboxes.
The Domino’s marketing team had assembled a variety of tools to measure marketing performance, keeping pace with the company’s rapid innovations. Unfortunately, measuring siloed analytics and channel-focused tools restricted the team’s ability to fully understand all of the different paths to purchase.
Find out how they worked around this challenge with Google Marketing Platform. Download the case study!
4860
Of your peers have already watched this video.
38:32 Minutes
The most insightful time you'll spend today!
Everything You Need to Know About Google Cloud ML Engine 101
Machine learning is all around us today. But data scientists and IT teams tasked with creating models have a hard time bringing together the right mix of ingredients—from data, infrastructure, tools, and APIs—to do their jobs effectively.
Google’s Cloud ML Engine eases many of the challenges data scientists and IT teams face. It’s a managed service that allows businesses to build and deploy their own models using any type or any size of data.
With Google’s Cloud ML Engine, data scientists can create models for training and prediction. And it provides APIs for these two building blocks.
Nikhil Kothari, Senior Staff Software Engineer, Google Cloud, breaks down Google’s Cloud ML Engine. He shows you how to use it as a service, so that data scientists can focus on data and on building models instead of managing infrastructure.
Achieving MLOps Excellence with Google Cloud and Equinix Collaboration
1244
Of your peers have already read this article.
3:30 Minutes
The most insightful time you'll spend today!
In recent years, machine learning (ML) has gained tremendous popularity as a powerful tool for solving complex problems across various domains. However, building and deploying ML models at scale can be challenging, as it involves a range of tasks such as data preparation, feature engineering, model training, deployment, monitoring, maintenance and so on.
According to “The Art of AI maturity” report published by Accenture “87% of data science projects never make it into production.” This is where MLOps comes in – it can help to address the core challenges by providing a framework for managing the entire ML lifecycle, from data collection and preparation to model development, testing, and deployment. It also reduces the time from ML model development to production and increases the success rate of ML projects.
In Google Cloud, we understand how important MLOps is to successfully productionize ML models. So we collaborated with Equinix, the world’s digital infrastructure company™ and a leader in global colocation data center market share, with 248 data centers in 27 countries on five continents. We helped them by providing the advisory services on the MLOps best practices and architecture.
Let’s take a sneak peek at the MLOps requirements at Equinix and the final architecture that was proposed.
What does MLOps mean for Equinix?
After multiple discovery sessions with the Equinix Team, we identified the core requirements and pain points to address in their new MLOps architecture:
- Reusability: Components such as features and pipeline components should be reused across projects to reduce costs and improve efficiency.
- Foundations: The foundations of the infrastructure, such as environments, folder structure, and project hierarchy, should be well-designed to support scalability and reliability.
- Early identification of problems: Problems should be identified early by including data validation, notifications, and retry mechanisms.
- Cost optimization: Costs should be optimized by paying only for what is used.
- Enterprise CI/CD requirements: Enterprise CI/CD requirements should be met by integrating with GitHub and GitActions.
- Scaling: The infrastructure must scale to support future growth.
- Security: Enterprise security requirements should be met in terms of IAM roles, network, etc.
MLOps Architecture
Based on the above requirements from Equinix, key design considerations were made for example – using Vertex AI Feature Store instead of Big Query for online feature serving, using DataFlow for pre-processing vs using the existing python based pre-processing and so on. After carefully assessing all the alternatives, the below reference architecture for MLOps in GCP was proposed:
Reference architecture for MLOPs using GCP is illustrated in Figure 1. This architecture includes the following pipeline stages:
- Vertex AI Workbench enables data scientists to quickly explore new ideas and develop/experiment new models. The source code is saved in GitHub repository
- Github Actions with self-hosted runners are integrated with Github as the source code repository. This enables continuous integration of code, quality and security scans. The artifacts generated during the process are saved in Artifact Registry and Google Cloud Storage. These artifacts are deployed to implement the pipeline.
- Unit tests and integration tests can be performed during the continuous integration in Github Actions with self-hosted runners. End-to-end tests are performed on demand in the continuous integration pipeline.
- Metadata about the artifacts is generated and saved in Vertex ML Metadata.
- Automated triggers can be enabled to run pipelines. For example, one trigger is the availability of new training data. These triggers can run the model training pipeline and the new trained model can be pushed to Vertex AI Model Registry.
- To train a new ML model with new data, the deployed Vertex AI Pipeline is executed.
- To train a new ML model with new implementation, a new pipeline will be deployed through CI/CD pipeline.
“The proposed architecture design covers the requirements and scenarios that we were looking for. As our AI and ML portfolio is growing in scale and complexity, it’s important to follow a clear and up-to-date architecture if we want to keep increasing the value delivered by our solutions. As part of the process, the team also acquired the skills required to fully implement it” according to Bernardo Fernandes, Data Science Senior Manager at Equinix.
Below is the snapshot of the features before and after MLOps implementation at Equinix:
As businesses increasingly rely on machine learning to gain a competitive edge, MLOps has become a critical component of their strategy. By adopting MLOps practices, organizations can achieve faster time-to-market, better performance, and higher ROI for their machine learning initiatives.
Fast track end-to-end deployment with Google Cloud AI Services (AIS)
The partnership between Google Cloud and Equinix is just one of the latest examples of how we’re providing AI-powered solutions to solve complex problems to help organizations drive the desired outcomes. To learn more about Google Cloud’s AI services, visit our AI & ML Products page.
We’d like to give special thanks to Nitin Aggarwal, Vijay Surampudi, Parag Mhatre and Anantha Narayanan Krishnamurthy for their support and guidance throughout the project. We are also grateful to the super awesome collaboration with the Equinix Team (Ravi Pasula and Brendan Coffey, Bernardo Fernandes, Łukasz Murawski, Jakub Michałowski, Sonia Przygocka-Groszyk, Marek Opechowski, Daria Bondara, Nila Velu, Vijay Narayanan, Dharmendra Kumar, Shailesh Sukare, Arunraj Kumar Raje, Seng Cheong Lee).
5143
Of your peers have already downloaded this article
7:30 Minutes
The most insightful time you'll spend today!
Sure, machine learning is becoming a business imperative, but how does it work in practice?
That’s the subject of a new step-by-step guide to solving business problems with artificial intelligence and ML, based on insights gathered by IDG Research Services.
Its publication comes at a time when technology leaders face growing pressure to embrace these emerging technologies, yet many have questions about how to get started.
It has real-life examples such as a health services company that used ML to reduce support ticket-resolution time from 48 minutes to six.
In another section, a financial services VP explains that cloud-based ML services enable his company to avoid spending money on computing resources that sit idle.
The guide also includes concrete tips for new ML adopters, provided by the CIOs and other IT leaders who participated in IDG’s research. For example, a real-estate CIO recommends the use of third-party tools that rely on AI and ML technologies, while a financial services VP highlights the challenge and potential of incorporating unstructured data into ML initiatives.
Download the guide now!
Increasing Production Efficiency: How AI Can Improve Asset Utilization and Minimize Downtime
2704
Of your peers have already read this article.
1:30 Minutes
The most insightful time you'll spend today!
Today, manufacturers are advancing on their factory digitalization journey, betting on innovative technologies to strengthen competitiveness, deliver sustainable growth, and offer new services. Macroeconomic factors – such as high energy costs, increasing labor, and raw material shortages – drive the need for urgent operational optimizations and automation.
Cloud capabilities have matured at an accelerated pace, giving manufacturers practical avenues to achieve these goals. Manufacturers are finding new ways to bring AI and machine learning (ML) to practical use cases, like predictive maintenance, anomaly detection, and asset utilization management. However, manufacturers struggle to adopt AI at scale due to challenges around data accessibility, infrastructure, and technology.
Google Cloud created purpose-built tools and solutions to organize manufacturing data, make it accessible and useful, and help manufacturers quickly take significant steps on this journey by reducing the time to value. In this post, we will explore a practical example of how manufacturers can use Google Cloud manufacturing solutions to train, deploy and extract value from ML-enabled capabilities to predict asset utilization and maintenance needs.
The journey to machine learning insights starts with accessible data
The first step to a successful machine learning project is to unify necessary data in a common repository. For this, we will use Manufacturing Connect, the factory edge platform co-developed with Litmus Automation, to connect to manufacturing assets and stream the asset telemetries to Pub/Sub.
After the telemetry messages are published to Pub/Sub, Dataflow will identify each message based on its structure and apply corresponding normalizations and transformations, which are preconfigured in Manufacturing Data Engine. Once the messages are processed, the messages will be routed to Cloud Storage, BigQuery, and/or Cloud BigTable based on user configuration.
Figure 1. High level architecture diagram of machine learning with Manufacturing Data Engine
To train a machine learning model, manufacturers can use Vertex AI AutoML to build a no-code model based on the training data stored in the Manufacturing Data Engine.
Then, users can trigger a batch prediction job in Vertex AI or export the AutoML model to run on the edge component of Manufacturing Connect for real-time prediction. Regardless of the model deployment methods, the prediction and explanation results will be ingested into Manufacturing Data Engine, which can be analyzed and visualized in Looker.
A blueprint for classifying asset condition
The following scenario is based on a hypothetical company, Cymbal Materials. This company is a factitious discrete manufacturing company that runs 50+ factories in 10+ countries. 90% of Cymbal Materials manufacturing processes involve milling, which are accomplished using industrial computer numerical control (CNC) milling machines. Although their factories implement routine maintenance checklists, there are unplanned and unknown failures that happen occasionally. However, many of the Cymbal Materials factory workers lack the experience to identify and troubleshoot failures due to labor shortage and high turnover rate in their factories. Hence, Cymbal Materials is working with Google Cloud to build a machine learning model that can identify and analyze failures on top of Manufacturing Connect, Manufacturing Data Engine, and Vertex AI.
For the pilot, Cymbal Materials forms a team of manufacturing engineers and data scientists to evaluate the feasibility of solving the tool wear detection problem. To avoid compliance concern, the Cymbal Materials team chooses to start with a public tool wear detection dataset hosted on Kaggle. This dataset is collected from running machining experiments on 2″ x 2″ x 1.5″ wax blocks in a CNC milling machine. The dataset contains measurements from the 4 motors (X,Y, Z axes and spindle) and program values in the CNC machine, which maps well to the data that Cymbal Materials collects for their CNC milling machines.
To start, the Cymbal Materials data scientists download the tool wear detection dataset from Kaggle and upload the dataset to Cloud Storage. Then, the data scientists use Vertex AI to:
- Perform exploratory data analysis using Vertex AI Workbench
- Train machine learning models using Vertex AI AutoML
- Deploy machine learning models to perform batch prediction and export AutoML models for edge deployment
- Interpret predictions using Vertex Explainable AI
After seeing great performance of the AutoML tabular model, the Cymbal Materials data scientists decide to use the AutoML model to predict on the actual CNC milling machine telemetries from their factories and validate the generalizability of the AutoML model. They ask the manufacturing engineers to deploy Manufacturing Connect in a Cymbal Materials factory and stream telemetries for one CNC milling machine to the Manufacturing Data Engine.
Manufacturing Connect includes an edge component that can gather data from manufacturing assets via an extensive library of 250+ communication protocols. The edge component of Manufacturing Connect comes with built-in Node-RED and Docker runtime, which support running custom workflows and machine learning models at the edge.
Using pre-defined hierarchies, Manufacturing Connect pushes asset telemetries and states to Pub/Sub.
After the factory operational data are ingested into Pub/Sub, Cymbal Materials uses Manufacturing Data Engine to:
- Normalize, transform, and contextualize real-time operational data with slowly changing metadata
- Batch ingest historical operational data and prediction results
- Route data dynamically to Cloud Storage, BigQuery, and/or Cloud BigTable
Figure 5. Manufacturing Data Engine configuration in Manufacturing Connect.
Using the trained AutoML tabular model and real-time telemetries from CNC milling machines, the data scientists trigger a batch prediction job on the CNC milling machine telemetries in BigQuery. The data scientists configure the batch prediction to output prediction results in Cloud Storage such that Manufacturing Data Engine can batch ingest the prediction results after the batch prediction job completes.
To consume the prediction results, the Cymbal Materials manufacturing engineers use Looker to create visualizations. The dashboard allows the manufacturing engineers to:
- Visualize the CNC milling machine actual and predicted tool conditions over time
- Explain the prediction results by summarizing the top attributing features
- Create alerts based on the predicted tool condition for their assets
- Take actions by contacting the supplier and/or scheduling maintenance for their assets
Figure 6. CNC mill wear prediction displayed in a Looker dashboard.
From edge to cloud, improving production efficiency for manufacturers
To support the entire factory digitalization value journey, manufacturers are looking for capabilities from simple visualizations to predictive ML models. Robust solutions, such as the one covered here, provide rapid paths for engineers to extract insight from their factory data.
Having a common data repository for manufacturing data, industry-leading machine learning platform, and versatile dashboard components accelerate manufacturer’s digital transformation.
This solution brings the best of Google Cloud’s data analytics and artificial intelligence capabilities in an industrial environment. Manufacturing Connect creates the link between industrial machinery and Manufacturing Data Engine, the cloud platform where the manufacturing data are processed, normalized, contextualized, and stored in a ready-to-consume format. Vertex AI can build, deploy, and scale machine learning models using data stored in the Manufacturing Data Engine. Vertex AI includes AutoML and Workbench for training models without code and training custom models with code-first experience respectively.
Learn more about how Google Cloud is transforming manufacturing to meet changing customer expectations at our Google Cloud Next Manufacturing playlist.
What’s next
More Relevant Stories for Your Company
Conversational AI in Search, Maps and Online Shopping!
Did you know about 77 percent of customers are likely to make a purchase from a brand they can message with? Direct interaction with the brand to gather product information shortens buyers' journey and personalizes it with appropriate messages. To helps businesses add speed, simplicity and convenience in brand-customers interaction,
Google Cloud Next ’22 to Commence in October: Block Your Calendar!
We’re excited to announce that Google Cloud Next returns on October 11–13, 2022. Join us for keynotes from industry luminaries and engage live with Google developers. Explore dynamic content across various learning levels, and dive deep into technologies and solutions spanning the Google Cloud and Google Workspace portfolios. Participate in breakout sessions,
Tyson Foods’ Story of Unlocking Opportunities by Integrating Real-time Analytics with AI and BI
As data environments become more complex, companies are turning to streaming analytics solutions that analyze data as it’s ingested and deliver immediate, high-value insights into what is happening now. These insights enable decision makers to act in real time to take advantage of opportunities or respond to issues as they
Google’s Latest ‘Carbon Footprint’ can Flag Users about Carbon Emission Levels from their Cloud Usage
Google Cloud is proud to support our customers with the cleanest cloud in the industry. For the past four years, we’ve matched 100% of our electricity use with renewable energy purchases, and we were the first company of our size to commit going even further by running on carbon-free energy 24/7
