Resolving Quality Issues In Food Manufacturing With Advanced Data Analysis

Chocolate production consists of several process steps where both raw material quality and storage conditions influence the final product quality. Although chocolate making today is largely based on science such as chemistry and food technology, the ‘human touch’ and flair based on many years of domain-specific knowledge remains an essential ingredient in the process.

Nidar AS is a major Norwegian chocolate producer with a 39,000 m2 production plant and 15,000 m2 of warehousing. Their factory has eight production lines which can produce a wide range of sweets. Over many years, Nidar has invested heavily to make their production processes more efficient, with a continual focus on improving efficiency, quality and health, safety & environmental performance.

Despite the investment in their production processes, the company began experiencing a quality problem in one of their product lines, forcing them to regularly scrap batches. From a business Nidar turned to multivariate analysis to get a deeper understanding and quantify their ‘gut feel’ of which process variables - and the relationships between them - determined product quality.

perspective, this resulted in significant waste, downtime, energy use and re-work costs. While Nidar had long experience using The Unscrambler® software for analyzing sensory data in product development, the application of multivariate analysis methods in process control was new to the company. However, when the quality issue arose, it was evident that to fully understand the complex variables at play, multivariate methods and Design of Experiments (DoE) strategies were required.