Website Preloader

Agri-food: predicting fermentation activity with Technord

2 Oct 24Data Science/IA, Food industry

The challenge

One of the main challenges in food production is to manage the variability of raw materials to deliver a final product that meets quality specifications. Champagne production is a case in point: the quality of the main substrate, the grape juice, depends on annual weather conditions, viticultural practices and the terroir in which it is grown. This means that fermentations will also behave differently depending on the composition of the juice (quantities of sugar and nitrogen, turbidity, among others).

Alcoholic fermentation involves the conversion of juice sugars by yeast into ethanol and CO2, and it has been found that the flow of CO2 generated is a reliable representation of fermentative activity. It is the main monitoring measure.

The challenge for the major champagne houses is to ensure that all fermentations run smoothly (golden batch). Harvesting takes less than a month, so hundreds of fermentation tanks have to be monitored. The variability of grape components means that each fermentation is different, and many parameters will influence it. The sheer volume and urgency of production means that oenologists cannot effectively monitor every tank during this period, and some fermentations may be out of specification.

The solution

Live, automated management of these fermentations is therefore of interest, so that fermentation behavior can be anticipated and corrected if necessary. This will guarantee wine quality and may also have a positive impact on production flow.

In the first phase, we were given just 6 fermentation curves to develop a model. Differential equations were developed to represent them. Physical modeling makes it possible to develop a representation of the process with just a few data, which is an advantage over statistical approaches. For “live” management of the measurements, a decision tree was designed to identify the context and guide the model to be used for curve prediction.

The second phase, using more data (fermentations with and without corrections), enabled us to refine the modeling and integrate the impact of corrections on fermentation behavior.

The next step is insertion into the process monitoring system.

The potential gain

The operational gain can easily be translated into financial gain, as it leads to better management of fermentations and fewer losses.

Further information on this project

Customer activity

  • Food industry
  • Production of high-end spirits

Solution brand

  • Wonderware
  • Historian
  • Siemens
  • Simcenter
  • Amesim
  • Matlab
  • Python

Type of work

  • Golden batch

Service

  • Decision-making tool

Technord news

More articles to discover.

Energy performance: setting up a complete visualization system

Find out how our teams helped our customer optimize its energy performance by controlling costs and improving its environmental impact through a visualization tool. Initial situation Our customer wanted to renew and modernize its control of energy networks.These...

Industrie 4.0: introduce AI to your industry with Technord

We're lifting a corner of the veil for you! Background to the approach Data is generated in every business line dedicated to industrial processes. As an industrial integrator of innovative solutions, Technord contributes to this process through all its business...

Success story for the MoM / MES department in the food industry

Our MoM/MES team was involved in renewing and modernizing the control of the global energy network at a major player in the natural mineral water production sector. Project challenge Our customer's mission is to offer consumers natural solutions to their hydration and...

Low-voltage project for Technord’s Industrial Electricity department

Find out how our industrial electrical experts helped install a new low-voltage mixer feeder. Customer challenge Following the success of its products, one of our customers, a major player in the industrial bakery sector, was faced with an urgent need to increase its...

Cost optimization for the food industry

The challenge Optimizing production and transport costs is a major challenge for any company operating on a global scale. In this case, the company in question has over 40 factories worldwide. Each plant manufactures some, but not all, of the company's products. Each...

Optimizing the moisture content of cement slag

The challenge In many mining and processing industries, such as the cement industry, rotary dryers are used at some stage in the process to dry large quantities of material. Controlling such a dryer presents several challenges. Firstly, the dryer consumes a lot of...

Data Science with Technord: real-time estimation of decarbonation rate

The challenge Cement production is quite complex and difficult due to the variability of raw materials, the different chemical reactions involved, and the inertia of devices such as a precalciner, a rotary kiln and a cooling system. The basic component of cement is...

Process modeling in the extractive industry

Find out how our Process Improvement team models the process to rationalize the amount of energy required and stabilize production. Initial situation Clinker, the basis of cement, is produced by calcining limestone around the clock. The resulting energy consumption is...

Increased output on a production line

Customer challenge A key KPI for measuring line performance is TRS (Taux de Rendement Synthétique ) or OEE (Overall Equipment Effectiveness). On the production line studied, the OEE is calculated in real time, but we observe that it fluctuates wildly from one hour to...

Cell culture: modeling biology and linking to monitoring flows

Customer challenge Scale-up of processes, i.e. scaling them up to a larger size, always requires careful thought, especially when they are bioprocesses: living beings behave in a very non-linear way. We need to understand the influence of environmental variables to...