A company needed to define the optimal duration of the blending process of a new food product. By deploying Chemometric Brain, our customer was able to identify the optimal blending duration for this product in a fast and accurate way, thus increasing productivity and reducing costs.
CONTEXT
A company specialized in animal nutrition deployed Chemometric Brain to analyze raw materials and final products, thus improving quality control. Chemometric Brain applied a qualitative analysis to detect changes in the ingredients’ composition that can come out after the manufacturing process.
A qualitative analysis uses the full spectrum available from a NIR device and treats it as a digital fingerprint. Chemometric Brain uses a number of mathematical models, such as Principal Component Analysis amongst others, to compare the fingerprint from the current batch to fingerprints from a library of ‘good’ fingerprints from previous batches or reference libraries. Chemometric Brain can then give the user a simple Tick or Cross advising if the batch is in line with the library for the product being tested.
TESTED PRODUCT
Samples from the first batch of a new blended food product.
ISSUE
Optimization of the mix-cycle duration of a new blended food product.
APPROACH
Our customer carried out an industrial test to determine the optimal duration of the mixing process of a new blended product. Samples were collected after 4, 6 and 8 minutes of blending at five different points of the container and at three different levels (top, medium and bottom).
To evaluate the duration of the blending process, a PCA model was built up in Chemometric Brain software with all the validation samples, defining a 99% confidence area. The ellipse around each sample group describes the variability of those samples, suggesting more or less homogeneity of the blending at a specific time.
As it can be observed in Figure 1, the size of the ellipses differs depending on the time. Taking into account that a smaller area of the ellipse indicates a greater homogeneity of the samples, the Chemometric Brain model suggested that the optimal mixing duration to obtain a homogeneous blending was 8 minutes.
Defining the optimal duration of the mix-cycle is key to improve cost-effectiveness and sustainability in the food industry.
By deploying Chemometric Brain in this company, our customer was able to identify the optimal blending duration for a new product in a fast and accurate way.
Our software enables any food company to easily adjust the blending process, thus increasing productivity and reducing costs.