{"id":13342,"date":"2024-10-23T12:20:16","date_gmt":"2024-10-23T10:20:16","guid":{"rendered":"https:\/\/www.inpro.de\/?p=13342"},"modified":"2025-07-03T17:55:05","modified_gmt":"2025-07-03T15:55:05","slug":"the-top-10-industrial-innovation-projects","status":"publish","type":"post","link":"https:\/\/www.inpro.de\/en\/the-top-10-industrial-innovation-projects\/","title":{"rendered":"Overview of 10 industrial innovation projects"},"content":{"rendered":"

<\/span>

<\/h1><\/div><\/div><\/div><\/div><\/div><\/div><\/div>

For over 40 years, we have been supporting industrial progress through collaborative innovation projects. The scope of the projects has changed over the years, but the methodical approach to innovation that we have developed and perfected with each project allows us to remain at the forefront of industrial innovation development. This includes bringing high-maturity innovations to a broader market as commercial solutions and turning investment costs into long-term profitability.<\/p>\n<\/div><\/div><\/div>

We present ten selected innovation projects, some of which are still ongoing, are being further developed in follow-up projects or are on their way to becoming commercial solutions. The diversity of our projects has one thing in common: they increase the degree of automation in production by using state-of-the-art, standards-based technologies and are scalable.<\/p>\n<\/div><\/div><\/div><\/div><\/div>

GenAI: Chatbots in production<\/h1>\n<\/div><\/div><\/div><\/div><\/div>

From time-consuming information searches to information at the touch of a button<\/h2><\/div>
<\/div>
\n

Thanks to generative AI, this use case presents a quick win for the manufacturing industry: the tedious task of studying technical documentation can now be streamlined by using customized AI chatbots, which allow users to search for specific information in dialog form, drawing from the content of existing manuals.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div>
<\/a><\/div><\/div><\/div><\/div><\/div><\/div>

Computer vision: Simulation of optimized robot controls<\/h1>\n<\/div><\/div><\/div><\/div><\/div>
<\/div><\/div>
<\/a><\/div><\/div><\/div><\/div>

From manual positioning of computer vision systems to virtual planning<\/h2><\/div>
<\/div>
\n

In practice, the integration of sensors and cameras in robot cells is still rarely planned virtually, which often leads to errors during bin picking\u2014i.e., the automated identification, removal, and sorting of objects from containers. Early virtual planning and testing of the machine vision systems can eliminate this weak point by optimizing the interaction of all interconnected elements.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div>
Further information on the use of
Computer Vision<\/span><\/a><\/div><\/div><\/div><\/div><\/div>

IDTA standard: Dynamic IT asset models<\/h1>\n<\/div><\/div><\/div><\/div><\/div>

From heterogeneous asset management to centralized standard models<\/h2><\/div>
<\/div>
\n

With IDTA – the administration shell – an industry standard for digital twins has been developed that enables the virtualization of industrial processes both within and across companies. We support the transformation of a heterogeneous IT landscape to a standardized IT asset model that drives the ongoing digitalization of mechanical engineering.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div>
<\/a><\/div><\/div><\/div><\/div><\/div><\/div>

AI: Automated process planning in logistics<\/h1>\n<\/div><\/div><\/div><\/div><\/div>
<\/div><\/div>
<\/a><\/div><\/div><\/div><\/div>

From manual definition of optimized logistics routes to automated route optimization<\/h2><\/div>
<\/div>
\n

The production processes sometimes involve several hundred individual parts that have to be provided from the warehouses at the right time, which involves a great deal of organizational effort and is sometimes prone to errors. Route optimization algorithms were integrated into an existing internal planning tool. Human-in-the-loop ensures that changes or adjustments are only approved by humans.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div><\/div><\/div>

Industrial metaverse: Virtual container showroom<\/h1>\n<\/div><\/div><\/div><\/div><\/div>

From analog part validation to virtual part testing<\/h2><\/div>
<\/div>
\n

Many operating resources are required in the field of body construction, including special containers in logistics. Due to their relatively small quantities and individual design, these containers require a great deal of planning and production effort. The Virtual Container Showroom enables cross-team development and approval of containers, which takes place in parallel and in a similar way to virtual vehicle and component development. Users can carry out important steps for the production release of the new container type virtually and interactively in the Industrial Metaverse.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div>
Further information about the
virtual container showroom<\/span><\/a><\/div><\/div><\/div>
<\/a><\/div><\/div><\/div><\/div><\/div><\/div>

Sustainability: Energy-efficient robotics<\/h1>\n<\/div><\/div><\/div><\/div><\/div>
<\/div><\/div>
<\/a><\/div><\/div><\/div><\/div>

From manual redesign of robot cells to digital resource optimization<\/h2><\/div>
<\/div>
\n

For an energy-optimized robot cell, various criteria such as room layout, conversion options, robot cycle times and the available budget must be taken into account. Without digital planning tools, resource optimization with simultaneous cost efficiency is not possible. Only through an automated analysis of all parameters can practicable solutions for an energy-efficient robot cell design be identified.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div><\/div><\/div>

Synthetic data: AI-supported inline inspection<\/h1>\n<\/div><\/div><\/div><\/div><\/div>

From real to synthetic production data for optimized inline inspection<\/h2><\/div>
<\/div>
\n

Defect data is often only available after the start of production (SOP), which makes early detection and processing more difficult. In addition, rare defects can only be trained and analyzed if they occur in sufficiently large numbers, which significantly limits the process. By using synthetic data, the need for real fault data for training can be reduced. Such AI is already available before the start of series production (SOP), which enables early preparation.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div>
<\/a><\/div><\/div><\/div><\/div><\/div><\/div>

Engineering & 3D-data: Point cloud conversion<\/h1>\n<\/div><\/div><\/div><\/div><\/div>
<\/div><\/div>
<\/a><\/div><\/div><\/div><\/div>

From disjointed CAD and scan data to a digital twin<\/h2><\/div>
<\/div>
\n

Importing large scan data into a factory’s CAE system is often difficult, which means that the systems are often based on outdated data. Flexible data conversion to JT format makes it easier to import into the CAE system. Factory designs can use up-to-date, real data, which enables better and more precise planning.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div>
Further information about our
conversion tool juno<\/span><\/a><\/div><\/div><\/div><\/div><\/div>

AI: Quality control in the paint store<\/h1>\n<\/div><\/div><\/div><\/div><\/div>

From offline rework to AI-based quality assurance<\/h2><\/div>
<\/div>
\n

Offline rework is often caused by faulty painting processes due to factors such as unadapted booth conditions, application parameters or material properties. As these causes are usually monitored in isolation and interactions are not taken into account, an AI-based quality assessment during the painting process can help. A quality-oriented warning and recommendation system reduces the causes of rework at an early stage and increases process efficiency.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div>
Further information on AI applications<\/span><\/a><\/div><\/div><\/div>
<\/a><\/div><\/div><\/div><\/div><\/div><\/div>

Self-organized production: Adaptive production flows<\/h1>\n<\/div><\/div><\/div><\/div><\/div>
<\/div><\/div>
<\/a><\/div><\/div><\/div><\/div>

From fixed production flows to dynamic program changes<\/h2><\/div>
<\/div>
\n

A hard-coded production flow offers little flexibility and only slow responsiveness in high-mix scenarios. In contrast, self-organizing production, supported by virtual PLCs and edge computing, enables rapid adaptation of the production flow and dynamic program changes during operation. This enables more efficient and adaptable control.<\/p>\n<\/div><\/div><\/div>

<\/div><\/div><\/div><\/div><\/div><\/div>
<\/div><\/div>
<\/i><\/span><\/div>

Collaborative Incubation<\/h2><\/a><\/div>
<\/div>
\n

Contact us for more information on joint industrial projects.<\/p>\n<\/div>

<\/div>Contact now<\/span><\/a>
<\/div><\/div><\/div>
<\/div><\/div><\/div><\/div><\/div><\/div>

Discover more<\/h1>\n<\/div><\/div><\/div>
\n\t