Assistance systems
Optimize engineering and operational processes
The Siemens Industrial Copilot is the first generative AI-supported assistant for engineering in the industrial environment. Siemens announces new functions for the Industrial Copilot and wins thyssenkrupp Automation Engineering as a global customer.
The Siemens Industrial Copilot for Engineering is the only copilot on the market that can write code for automation technology. Future features include multimodality and agent concepts that will further facilitate the work of engineers. There are also plans to offer the Siemens Industrial Copilot for Operations as an on-premises-based hardware-software bundle to give users full control over their own data.
Rainer Brehm, CEO Factory Automation at Siemens, said: “With Siemens' comprehensive industry know-how, we are implementing generative AI in industrial-grade solutions that can be used without any special AI expertise. The Siemens Industrial Copilot, the first generative AI-supported product for engineering in the automation industry, is a catalyst for industrial automation and helps our customers to increase innovation, productivity and improved competitiveness."
Thyssenkrupp Automation Engineering and Siemens Electronics Factory: Rollout Siemens Industrial Copilot
Competitive pressure and a shortage of skilled workers are the major challenges for industrial companies. The introduction of industrial-grade, generative AI to the shop floor has enormous potential to overcome current industrial challenges and improve productivity. According to a recent study by Gartner, by 2028, 75 percent of developers will regularly use generative AI to support code creation. By comparison, at the beginning of 2023, fewer than 10 percent of developers did so.
Thyssenkrupp Automation Engineering, a special machine and plant manufacturer, has integrated the copilot for engineering into a battery machine used to test the quality of electric vehicles. The industrial company plans to use the assistant controlled by generative AI on a large scale. From 2025, the systems at Thyssenkrupp's global locations will be equipped with the AI assistant.
The Industrial Copilot supports engineers in creating TIA Portal projects. It helps them to develop SCL (Structured Control Language) code for programmable logic controllers (PLCs) more quickly, intelligently integrates the code into the TIA Portal and creates machine visualization in WinCC Unified. This allows engineering teams to reduce repetitive and monotonous tasks such as automating data management or sensor configuration. This allows them to work more efficiently and concentrate on improving processes and driving innovation.
"Thyssenkrupp Automation Engineering and Siemens have a long and successful collaboration," said Dr. Rolf-Günther Nieberding, CEO of Thyssenkrupp Automation Engineering. "I expect that the rollout of the Siemens Industrial Copilot will enable us - and thus our customers - to implement complex projects in a much shorter time."
The Siemens Erlangen equipment plant implemented the Copilot for Operations in its soldering machines. The Industrial Copilot helps plant operators and maintenance technicians to understand a machine's error code and translates the message into natural language. It suggests solutions that are tailored to the specific characteristics and history of a machine by searching through various documents, manuals or spare parts lists. Machine downtimes are thus significantly reduced, production bottlenecks can be resolved more quickly and shift changes run more smoothly.
Multimodality, agent concepts and on-premises model optimize Siemens Industrial Copilot
The development of expanded and more powerful functionalities for the Siemens Industrial Copilot played a key role in winning thyssenkrupp Automation Engineering as a customer. The Industrial Copilot for Operations enables production employees to interact directly with machines. It supports them in maintenance tasks, in detecting and processing machine errors and helps to improve machine performance.
In addition, the Industrial Copilot will have multimodal functions for analyzing and interpreting images and will increase productivity in the future through agent-based automation for numerous tasks. To ensure the security of customer data and to ensure that no data leaves the shop floor, the Industrial Copilot for Operations will in future be offered as an on-premises-based hardware-software bundle with the Simatic industrial PC (IPC 1047E).
The software stack running on IPCs is based on Nvidia NIM Microservices that are part of the Nvidia AI Enterprise software platform that enable automation and maintenance engineers to make real-time queries on operational and document data. This enables fast decision-making and reduces machine downtime. The configuration does not require an internet connection and stores data on local hardware devices. This ensures data security because all customer data is processed directly on the shop floor, stored there and is still available whenever and wherever it is needed.
The Industrial Copilot for Engineering supports multimodal input, for example by recognizing and converting manual changes in the ECAD document used for electrical planning. These changes are automatically highlighted, commented on and finally implemented in the TIA Portal project.
Highly complex automation projects are partially automated by agent concepts. Agent concepts go beyond simple question-and-answer interactions and automate processes by breaking down large, complex tasks into subtasks. All relevant information is then collected from different sources, including ECAD information, to understand the user's goal.
Agents can also be connected to external systems and sources, creating a closed loop in which different tools are linked together. They then create a plan for how to achieve the goal and carry out the necessary actions independently. This can be, for example, sending messages, accessing external systems or updating data records. In addition, engineers can use agents to control all production processes - with full transparency, an overview of all data and knowing what the next steps are.
The Engineering Copilot TIA Essential has been available on the Siemens Xcelerator Marketplace since July 2024. While Siemens provides the automation part of the Industrial Copilot, natural language processing is carried out by one of the most powerful GPT models via the Azure OpenAI service in the Microsoft Cloud. This ensures performance, data protection and reliability at the highest level. Siemens' generative AI solutions for industry are reliable, secure and trustworthy - they make industrial AI accessible to everyone, anytime, anywhere.