Problem Statement
Universal challenge faced across Foods & Beverages, FMCG, and Pharmaceutical manufacturing industries due to Weight or Volume declaration on packaging. Example below illustrates this:
Overweight Issue
Extra grams of chocolate given to consumer above declared Wt. to avoid legal non-compliance.
Legal Requirement
In India, for 51 g chocolate, avg. Wt. of 125 randomly picked bars from one shift manufacturing must exceed 51 g.
Operational Set-Point
Hence Chocolate depositor is often set to deposit 52 g of chocolate in moulds, leading to excess.
Cost of Overweight
It is significant and a major margin eroder.

Current Industrial Reality

Despite massive investments in Digital Dashboards, Quality Systems, quality Lab instruments, process SCADA systems, and sophisticated Field sensors, most manufacturing plants struggle to convert this expensive Data into Yield loss reduction.

Current Industrial Reality

Measured. Logged. Forgotten.

Plant Quality teams operate sophisticated analytical instruments and collect samples every shift, day and night, to meet R&D-defined specifications. Does this expensive data remain trapped and vanish with their registers instead of driving operational excellence?

Measured Logged Forgotten

Sensors Generating Data, Not Intelligence.

Hundreds of sophisticated field sensors generate massive data every milli-second to control real-time production. But are we truly leveraging this data for a closed feedback loop—or simply letting it auto-delete from hard drives?

Sensors Generating Data

Judgement-Led Manufacturing

Depending on years of experience, educational background, analytical capabilities, and motivation level for on-floor settings tuning of chocolate Depositor, liquid bottle Filler, liquid tetrapak Filler, biscuit Rotary Moulder, biscuit Rotary Cutter, Multihead Weigher, noodle Cutter, chocolate Enrober, and many more?

Judgement Led Manufacturing

The Solution

Deep Learning AI Model

Built from first principles of Engineering and Mathematics (see ellipse diagram), a cutting-edge Neural network designed to precisely control Weight or Volume of product in Closed feedback loop AI Manufacturing process. Following example illustrates it:

Vectors & Matrices First, Second, and Third order Partial Differential Equations Stochastic Probability Distributions Fluid Mechanics Heat Transfer Thermodynamics Chemical Reaction Engineering Electrical & Control Systems GPU Computation
10 sensors 6 sensors 33 sensors 6 parameters
42 sensors 4 sensors 12 sensors 11 sensors 9 parameters
84 parameters
Every 15 mins Multi-Output Deep Neural Network Model Paste Mixer (mixes milk powder, cocoa butter, sugar) Refiner (reduces mix particle size by crushing) Conch (develops chocolate flavors by Mallard Chemical reactions) Quality lab data Auto-correction of Depositor settings Chocolate Storage tanks Chocolate Service tank Temperer (Nucleation & growth of Form-5 Crystals) Depositor (deposits liquid chocolate on plastic moulds) Quality lab data Cooling Tunnel (only chocolate bars sample collection at exit) Quality lab data