Quality assurance

What is the challenge?

Quality assurance includes all measures to ensure defined quality requirements. They take place in every company in many different areas and designs. For example, the quality of individual products (such as components or foodstuffs), the safety of processes and the quality of consulting and other services are recorded and checked. The identification of counterfeits also falls within the scope of quality assurance. Manual quality control is time-consuming and cost-intensive and can be prone to errors.

What data can help?

• Product and production data
• Image and sensor data (vibration, noise deviations)
• Relevant data from newspapers, reports and news (information on quality and for possible recall actions)
• Customer feedback

How can companies use their data?

The use of data analysis can help automate and thus accelerate quality assurance processes and increase measurement quality. For example, image data of product parts are compared. Medial data and report information can be incorporated into an early warning system to indicate quality deficiencies at an early stage. This can be followed by more specific quality checks. The core of data analyses for quality assurance are deviation analyses from the target or from defined quality requirements. In addition, companies can better derive their options for action if messages are generated from the data analyses to indicate the deviations or if probable deviations are predicted.

Where is this use of data already being applied?

The “TotalSense” and “LumoVision” programs of the Bühler technology group assess the quality of food products, for example rice grains, on the basis of image files and fluorescent color.

The IT company Elunic supports quality assurance with an optical inspection of production quality. Images are recorded and evaluated using a camera and illumination system. Data analysis can be used to detect defects on surfaces. The software is used, for example, by BMW, Braun and QCells.

The chemical company BASF collects data on accidents and safety-related incidents. This enables a deeper root cause analysis of such events to increase process safety and quality.

Technology group Bosch uses IoT data to improve the quality of its products and adapt them to customer use. Automatic feedback loops are also used to transmit error messages. In this way, usage and error messages can be linked and product adjustments derived.

How does this use of data contribute to value creation?

The use of data in quality assurance can increase its efficiency. The early indication of quality defects saves costs for later corrections, faulty production or recalls. Higher quality is often associated with greater trustworthiness and better customer loyalty. New offers and services for quality assurance in the after-sales area can also lead to new value creation.

Sources: Bühler AG (2019), Elunic AG (2019), BASF (2017), Bosch (2019)