How Small and Medium-Sized Businesses Are Using Data to Make Their Production Smarter and More Efficient

The Dutch manufacturing industry faces a twofold challenge: customers expect greater flexibility and customization, while labor shortages, rising costs, and tight margins are putting pressure on production capacity. At the same time, machine learning (ML) offers concrete opportunities to produce more efficiently, reduce errors, and make better data-driven decisions.

‍

In this white paper, we highlight two practical applications of machine learning that are directly relevant to SME manufacturing companies: visual quality control and process optimization.

‍‍

Application 1: Automated Quality Control Using Computer Vision

‍

Case Study:
A plastic injection molding company in Almelo manufactures technical parts for the automotive industry. The quality requirements are high: even the slightest warping or discoloration can result in the customer rejecting the parts. Until recently, employees inspected the parts manually for visible defects. This regularly led to defects being missed, resulting in returns and additional costs.

‍

Solution
The company installed a camera system at the discharge point of the injection molding machines and linked it to a machine learning algorithm trained on thousands of sample images of correct and defective products.

‍

How It Works

• During production, the camera continuously captures images of each component
• The algorithm compares these to the ideal profile and detects deviations such as air pockets, burrs, and discoloration
• Defective parts are automatically removed from the line

‍

Result

• 95% of errors are now detected automatically
• The number of returns fell by 60%
• Customer satisfaction and delivery reliability increased noticeably
• Operators can focus on the process rather than visual inspection

‍

This application led to an immediate improvement in quality, lower costs, and higher output per FTE.

‍‍

Application 2: Process Optimization Through Data Analysis

‍

Case Study:
A metalworking company in North Brabant manufactures parts in small batches on three production lines. The schedule appeared to be efficient, but the production manager suspected that the lead time was longer than necessary. There was no clear data on where in the process delays were occurring.

‍

Solution
Working with a data specialist, the company collected data from the PLC systems, the ERP system, and through manual input from the operators. A machine learning model was then trained to identify bottlenecks in the process.

‍

 So what happened?

• Setup times varied greatly among teams, especially for more complex tasks
• Shift handoffs resulted in an average delay of 20 minutes per shift
• One production line was consistently less efficient due to incorrectly planned batch sizes

‍

Promotions

• The setup procedures have been standardized based on best practices from the model
• The team handover was updated with a digital handover form
• Production planning was optimized based on data analysis

‍

 Result

• The average turnaround time decreased by 14%
• Output per shift increased by 11% without any additional hours
• Operators are more engaged thanks to insights into their performance

‍

This project demonstrates that even simple data insights, when combined with machine learning, can lead to tangible improvements in efficiency and engagement.

‍

Conclusion

Machine learning is not some distant vision of the future. Small and medium-sized manufacturing companies in the Netherlands are already using it to improve quality and streamline production processes. Visual inspection and process optimization are two accessible applications that deliver quick results when implemented correctly.

‍

TMC Media helps manufacturing companies translate this technology into clear strategies and communication. Whether you’re already collecting data or just looking for a practical starting point, we’ll help you take concrete steps toward smart manufacturing. 

‍