How Artificial Intelligence Transforms Manufacturing

summary

According to a survey by the World Economic Forum, more than 70% of industrial AI projects have been abandoned after the pilot phase. While some companies integrate artificial intelligence (AI) into their businesses to achieve important economic benefits, some face major challenges. However, many examples demonstrate that AI can be used effectively in manufacturing, making it a key component of flexible and efficient production (Figure 1). Currently, AI solutions are available that not only allow smooth integration into industrial processes, but also handles highly efficient and complex tasks.

Visual quality control

Quality assurance is an important task in industrial manufacturing. An AI-equipped image processing system allows for reliable quality inspections. One example is Inspekto. It is a visual quality inspection solution that allows businesses to automate product checks without the need for deep AI or image processing knowledge. The intuitive system will be available within an hour and only requires around 20 sample images classified as “good” to provide accurate results. Basic production knowledge about quality testing is sufficient. No AI expertise is required (Figure 2).

For example, the medium-sized company MTConnectivity Power2PCB uses InspekTo to inspect connectors to identify minimal deviations and slightly bent contacts. By integrating this AI-based system into the production line, the company ensures continuous quality assurance, improves reliability and reduces delivery time.

Generation AI in manufacturing

The application and implementation of the generated AI model is more complicated. Siemens industry personnel are designed to improve human machine collaboration, from design, planning, engineering to operation and service, and accelerate innovation across the value chain. Currently, industrial personnel are piloted at the customer site and at the Siemens plant to test its reliability. Meanwhile, industrial co-pilots for engineering are already available as finished products (Figure 3).

A specialized machinery and equipment manufacturer, Thyssenkrupp Automation Engineering integrates Siemens Industrial Copilot into the system to handle round cells used in battery inspections in electric vehicles. Copilot automates recurring tasks such as data management, sensor configuration, and detailed reports that help you meet strict battery inspection standards. By managing routine tasks, Copilot allows engineering teams to focus on complex, valuable activities, solve problems in real time, minimize downtime and ensure smooth production.

Predictive maintenance with AI

AI is also revolutionizing predictive maintenance. Instead of relying on fixed maintenance intervals and manual analysis, AI uses continuous mechanical data monitoring to detect initial signs of wear and propose maintenance actions. Siemens’ Siemens’ predictive maintenance solution identifies deviations in temperature, vibration and torque data and provides early warnings and recommendations (Figure 4).

Mercer Selger, a producer of pulp and wood products, uses this technology to monitor the machine in real time. Data from multiple production lines is combined into a central platform that provides a complete overview of the manufacturing process and significantly reduces downtime.

Seamless integration of AI models

Even companies that already employ AI are facing challenges when expanding their solutions. It often causes problems such as time-consuming updates, poor connections, and complicated maintenance. Industrial AI suites are available to address these challenges. Industrial AI Suite is a platform for smooth implementation of AI solutions on the shop floor.

These solutions combine existing AI expertise with Siemens infrastructure for scalable deployments, working closely with customers to customize them. Depending on your use case, these solutions use edge or cloud computing to integrate services such as AWS and Microsoft Azure. AI models can be trained in the cloud and easily deployed to production floors using AI Incerence Server. Industrial Edge applications allow customers to deploy and run AI models directly trained at the industrial edge, even using GPU-accelerated inference.

The Industrial AI Suite also manages the full AI model lifecycle, allowing you to easily update and auto-detect performance issues. For example, Siemens helped food and beverage companies integrate AI-based soft sensors into their production. These sensors ensure consistent product quality and taste by analyzing process parameters in real time, dynamically adjusting target values ​​to optimize production and reducing waste.

Electronics manufacturing uses machine learning models to detect circuit board assembly errors at Siemens’ electronics factory in Erlangen, Germany. This increases speed and cost-effectiveness with the help of industrial AI suites.

Make AI accessible and practical

These real-world examples illustrate the importance of AI in modern industry. Embedding AI systems into products hides complexity from users and makes AI accessible and usable for everyone. The key to success lies in flexible infrastructure that allows businesses to tailor AI solutions to their specific needs.
Industrial AI is no longer a futuristic vision. Today, it already offers real competitive advantages.

Image courtesy of Siemens.

This feature was originally featured in the June/July issue of Automation.com Monthly.

Download the June/July issue of Automation.com every month