From augmented reality to digital twins.


From augmented reality to digital twins.

Digitisation is familiar territory for development service providers, while at the same time opening up completely new opportunities. Agile development methods, augmented reality, digital twins, artificial intelligence, predictive maintenance and autonomous driving are all based on the latest digital technologies.

Bertrandt has customers in a wide range of industries from automotive and medical technology to machinery manufacturing and plant engineering. One thing which all these industries have in common is that the value chain consisting of design, development, manufacturing and delivery to the customer is becoming much shorter as a result of digitisation.

  • Mechanical engineering companies which provide a virtual digital twin can offer their customers new services. The machines that are installed on customers’ premises can send their data back to the virtual twin. This makes it possible to fine-tune the operation of the machine and to schedule predictive maintenance using intelligent algorithms.
  • The design and development departments can use the digital twin to identify weak points and to exploit the potential for improvements.
  • The virtual model of the machine also allows simulations to be created. Virtual investigations of the space available for installing new components make it possible to see how they can be integrated. In addition, critical parts can be subjected to thermal stresses at an early stage of the development process.

Bertrandt has the expertise needed to create digital value chains, as well as extensive experience from a number of successful projects, including recording machine data, data storage, analysis of large volumes of data and developing and visualising virtual models.

Production machinery and plants often have a service life of 20 years or more. However, older machines are more likely to break down and need more frequent maintenance. This makes it all the more important to integrate these machines into an automated monitoring system so that the potential of predictive maintenance can be fully exploited:

  • Where machines and plants have no suitable interface, Bertrandt equips them with an IoT device for recording machine data.
  • The device consists of a sensor, a transmission unit and a computer with the appropriate software for pre-processing the data.
  • This allows parameters such as temperature, pressure and vibration and key figures such as throughput to be continuously recorded.

The machine data is kept in a local storage system or sent to the cloud. Bertrandt can develop the software for all stages of the process. We have completed a large number of projects that involved processing data in the cloud.

Which data are needed? How can the quality of the data be measured? How can connections within the data be identified? What added value does the evaluation of the data bring?  We advise companies on how to use this data to identify the causes of faults and to improve performance and enhance designs.

The Bertrandt Industry Cloud (BIC) is our own modular solution based on concepts for data fusion, data analysis, machine learning and algorithm development.  The advantage that we have over big data service providers is our 40 years of industry expertise. We have an in-depth understanding of design, development, production and support, which enables us to distinguish non-relevant data (white noise) from usable data during the analysis process.

Key features of our portfolio of services:

  • Production analyses and fault visualisation
  • Neural networks and machine learning
  • Selecting, configuring and modelling data
  • Microsoft Azure Cloud services (IoT Suite), Microsoft Gold Partnership for cloud services
  • SQL, NoSQL, Hadoop, data lake technologies
  • Kafka
  • Transferring data using the MQTT (Message Queuing Telemetry Transport) protocol

Examples of projects involving data-based services

Automated labelling of image data
A neural network had to be trained to assess image data for an autonomous driving project in the automotive industry with the aim of improving the environment detection process using cameras. Machine-readable descriptions needed to be assigned to more than 50 million images of road scenes using an automated process. We are currently developing high-performance algorithms for this purpose, together with a toolkit for the automated labelling of image data.

Identifying component faults by analysing vibrations
A defective vehicle component developed reproducible cracks while the vehicle was being driven, which had no obvious cause. We carried out an analysis which involved correlating the component’s vibration data with the lateral and longitudinal acceleration of the vehicle. This allowed us to identify that the thickness of the material used to make the component was incorrect and was causing the problem, because it had led to destructive vibrations.

Evaluating the quality of the road surface using vehicle shock absorbers
The aim of the project was to evaluate the quality of the road surface on the basis of the behaviour of vehicle shock absorbers. An external service provider specialising in data analysis was unable to produce any plausible results despite the use of machine learning and neural networks. The company had no knowledge of the industry and no understanding of driving dynamics. The data analysts from Bertrandt succeeded in drawing valuable conclusions about the quality of the road surface on the basis of their industry expertise, mathematical-statistical methods and application-specific algorithms.

The advances made in the development of autonomous driving systems are directly linked with the creation of virtual test methods. The extreme complexity of autonomous driving functions leads to the need for a huge number of tests, which can only be carried out in virtual form. Bertrandt has used its extensive experience of validating driving functions in the automotive industry to set up virtual test environments.

We use virtual processes to test individual components, integrated systems and the interaction of a variety of complex systems for automated driving.

Examples include:

  • Driving dynamics simulators
  • Scenario-based testing
  • Hardware-in-the-loop (HiL) testing for virtual crash tests
  • Model-in-the-loop (MiL) testing for driving functions
  • Software-in-the-loop (SiL) testing for classic functions

Bertrandt uses virtual reality (VR) and augmented reality (AR) methods to develop applications for research and development, production and logistics. These are used in marketing, servicing and maintenance, as well as for training and education purposes. Bertrandt is in the final stage of the certification process to become a Microsoft HoloLens partner.

Examples of projects include:

  • Visualising fluid simulations with thermal and aerodynamic processes
  • Virtual investigations of installation spaces before components are actually fitted
  • Positioning machines and robots in virtual factory buildings
  • AR applications for car dealers that allow them to demonstrate different equipment levels and new functions on real cars
  • Instructions on installing spare parts and additional information about individual components supplied via an AR headset for service engineers
  • Investigating error messages in service departments without having to remove components
  • VR training on assembly instructions for employees. Virtual repairs carried out by service engineers before they work on real objects