Predicting and enhancing shelf life of produce in storage

Patent metadata

Field	Value
Publication number	US-2025035373-A1
Application number	US-202418752849-A
Country	US
Kind code	A1
Filing date	Jun 25, 2024
Priority date	Jul 25, 2023
Publication date	Jan 30, 2025
Grant date	—

Abstract

This disclosure relates generally to shelf life of produce and, more particularly, for predicting and enhancing shelf life of produce in storage facility. A significant quantity of produce such as fresh fruits and vegetable are lost before reaching the consumer, during its long-term storage in a warehouse or a storage facility. Many techniques have been employed to preserve-enhance the shelf life. However, the existing techniques do not explicitly consider factors such as air circulation, stacking of container, and respiration of the produce during shelf-life prediction. The disclosed techniques predict and enhance the shelf life of produce in storage facilities in several steps including determining a set of modelling parameters, determining a plurality of shelf-life parameters, predicting a shelf life of the produce based on generating a shelf-life prediction model, predicting a quality index and finally, enhancing the shelf-life of the produce based on an optimization technique.

First claim

What is claimed is:

1 . A processor implemented method, comprising:
receiving a plurality of inputs, wherein the plurality of inputs are associated with a plurality of produce and a storage facility, and the plurality of inputs comprises a produce information and a storage facility information, wherein:
the produce information comprises a produce, a plurality of properties of the produce including a volume, a shape, a size, a weight, an initial surface temperature, harvesting details, and
the storage facility information comprises:
a plurality of containers and a type of each container from the plurality of containers, and
a plurality of storage parameters comprising an inlet air temperature, an air flow rate, a set of environmental conditions and a produce harvesting details;

determining a set of modelling parameters for a produce from the plurality of produce, based on a process modelling technique using the plurality of inputs, wherein the set of modelling parameters comprises a respiration of gases condition, a mass loss condition, a cumulative gas index and a heat source; determining a plurality of shelf-life parameters for the produce and the storage facility using the set of modelling parameters, based on a modelling technique wherein the plurality of shelf-life parameters comprises a respiration gases concentration, a temperature, a humidity, a mass loss, and a cumulative gas index for a predefined time interval; predicting a shelf life of the produce using the plurality of shelf-life parameters based on a data analysis technique, wherein the data analysis technique comprises:
generating a shelf-life prediction model based on a shelf-life prediction model technique,
predicting a quality index using the shelf-life prediction model, and
predicting the shelf life of the produce based on the quality index for the produce, and
enhancing the shelf-life of the produce based on an optimization technique, wherein the shelf-life of the produce is enhanced by optimizing the plurality of storage parameters for the plurality of container based on the shelf-life.

2 . The method as claimed in claim 1 , wherein the storage facility is one of a warehouse, or a moving air-conditioned vehicle and the plurality of produce comprises of one of a plurality of vegetables, a plurality of fruits, a variety of meat and a combination thereof.

3 . The method as claimed in claim 1 , wherein the process modelling technique comprises an enzyme kinetic model and a mass loss model and the cumulative gas index comprises a carbon dioxide gas index, an ethylene gas index, and a methane gas index.

4 . The method as claimed in claim 1 , wherein the modelling technique comprises one of a Computational fluid dynamic (CFD), a Physics-informed neural networks (PINNs), and a Smoothed-particle hydrodynamics (SPH).

5 . The method as claimed in claim 1 , wherein the plurality of shelf-life parameters are determined using the set of modelling parameters based on Computational fluid dynamic (CFD) technique in several steps including creation of a geometry of each of the produce and the storage parameter, generating a mesh for the geometry of each of the produce and the storage parameter, applying the set of modelling parameters to the mesh based on the plurality of inputs, and simulation and post-processing.

6 . The method as claimed in claim 1 , wherein the shelf-life of the product is represented by a quality index indicating a number of days that the produce is fresh and safe for use and the shelf-life prediction model technique comprises one of a machine learning model, a data-based model, and an empirical model.

7 . The method as claimed in claim 1 , wherein the shelf-life of the produce is enhanced in a plurality of steps including (a) assigning a quality index for each of the plurality of crates and (b) optimizing the plurality of storage parameters to enhance the shelf-life of the produce based on the assigned quality index using the optimization technique, wherein the optimization technique comprises a bayesian optimization, a gradient base optimization, a genetic algorithm, and an exact method.

8 . A system, comprising:
a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
receive a plurality of inputs, via one or more hardware processors, wherein the plurality of inputs are associated with a plurality of produce and a storage facility, and the plurality of inputs comprises a produce information and a storage facility information, wherein:
the produce information comprises a produce, a plurality of properties of the produce including a volume, a shape, a size, a weight, an initial surface temperature, harvesting details, and
the storage facility information comprises:
a plurality of containers and a type of each container from the plurality of containers, and
a plurality of storage parameters comprising an inlet air temperature, an air flow rate, a set of environmental conditions and a produce harvesting details;

determine a set of modelling parameters for a produce from the plurality of produce, via the one or more hardware processors, based on a process modelling technique using the plurality of inputs, wherein the set of modelling parameters comprises a respiration of gases condition, a mass loss condition, a cumulative gas index and a heat source;
determine a plurality of shelf-life parameters for the produce and the storage facility using the set of modelling parameters, via the one or more hardware processors, based on a modelling technique wherein the plurality of shelf-life parameters comprises a respiration gases concentration, a temperature, a humidity, a mass loss, and a cumulative gas index for a predefined time interval;
predict a shelf life of the produce using the plurality of shelf-life parameters based on a data analysis technique, via the one or more hardware processors, wherein the data analysis technique comprises:
generating a shelf-life prediction model based on a shelf-life prediction model technique,
predicting a quality index using the shelf-life prediction model, and
predicting the shelf life of the produce based on the quality index for the produce, and
enhance the shelf-life of the produce based on an optimization technique, via the one or more hardware processors, wherein the shelf-life of the produce is enhanced by optimizing the plurality of storage parameters for the plurality of container based on the shelf-life.

9 . The system as claimed in claim 8 , wherein the storage facility is one of a warehouse, or a moving air-conditioned vehicle and the plurality of produce comprises of one of a plurality of vegetables, a plurality of fruits, a variety of meat and a combination thereof.

10 . The system as claimed in claim 8 , wherein the process modelling technique comprises an enzyme kinetic model and a mass loss model and the cumulative gas index comprises a carbon dioxide gas index, an ethylene gas index, and a methane gas index.

11 . The system as claimed in claim 8 , wherein the modelling technique comprises one of a Computational fluid dynamic (CFD), a Physics-informed neural networks (PINNs), and a Smoothed-particle hydrodynamics (SPH).

12 . The system as claimed in claim 8 , wherein the plurality of shelf-life parameters are determined using the set of modelling parameters based on Computational fluid dynamic (CFD) technique in several steps including creation of a geometry of each of the produce and the storage parameter,

Assignees

• Tata Consultancy Services Ltd

Inventors

• Kapse Shrikant Arjunrao
• Kulkarni Hrishikesh Nilkanth
• Kausley Shankar Balajirao
• Ahmad Dilshad
• Rai Beena
• Kedia Priya

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• F25D29/00 Primary

  Arrangement or mounting of control or safety devices · CPC title

• G06Q10/0832

  Special goods or special handling procedures, e.g. handling of hazardous or fragile goods · CPC title

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• G06Q10/04

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title