METHOD AND SYSTEM FOR PREDICTING OPTIMAL LOAD FOR WHICH THE YIELD IS
MAXIMUM BY USING MULTIPLE INPUT ELECTROLYZER PARAMETERS filed by RIPIK TECHNOLOGY PRIVATE LIMITED
This patent describes a system to optimize operations in manufacturing facilities that use electrolyzers. Electrolyzers split water into hydrogen and oxygen using electricity. Their electrical load levels impact costs and efficiency.
The present invention uses AI and machine learning to predict the best way to allocate load across multiple electrolyzers. This maximizes total yield for the manufacturing plant while minimizing electricity costs.
It takes into account equipment factors like the capacity of each electrolyzer. It also considers constraints like raw material supply and product storage limits. The system models chlorine evacuation too since that can hinder caustic soda output.
The algorithms are capable of processing the many complex variables at play. No easy spreadsheet could accomplish this modeling. A type of mathematical optimization called "swarm optimization" is applied. Examples are genetic algorithms and particle swarm optimization.
The AI system keeps adapting its load recommendations based on data coming into its monitoring dashboard. Operators can customize certain parameters but the software is configuring most of the decision logic automatically.
The inventors claim results show their AI optimizer significantly cutting power consumption and costs versus alternatives. Smart coordination of multiple electrolyzers is complex. This technology handles the data analysis to efficiently divide load distribution.
In essence, the patent discloses an intelligent electrolyzer load prediction platform. It leverages AI to boost manufacturing performance while reducing electricity usage. Company managers can see optimized operations guidance on easy dashboard interfaces. It aims to save power, costs and effort through algorithmic process coordination.
WordPress Websites for Engineers: Elevate Your Brand
METHOD AND SYSTEM FOR PREDICTING OPTIMAL LOAD FOR WHICH THE YIELD IS MAXIMUM BY USING MULTIPLE INPUT ELECTROLYZER PARAMETERS .pdf
1. FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(Ref section 10 and rule 13)
1. TITLE OF THE INVENTION
METHOD AND SYSTEM FOR PREDICTING OPTIMAL LOAD FOR WHICH THE YIELD IS
MAXIMUM BY USING MULTIPLE INPUT ELECTROLYZER PARAMETERS
2. APPLICANT
a. Name: RIPIK TECHNOLOGY PRIVATE LIMITED
b. Nationality: INDIAN
c. Address: A606, B-9/1A, Designer Park, Sector No-62, Noida, Gautam Buddha
Nagar, Uttar Pradesh-201309
3. PREAMBLE TO THE
DESCRIPTION
PROVISIONAL
The following specification describes the
invention.
2. BACKGROUND OF THE INVENTION
Field of the Invention
[001] Embodiments of the present invention relates generally to systems, methods,
devices, and apparatus to leverage data parameters to predict optimal load for which the
yield is maximum. More particularly, to deployable controlled systems and methods for
the manufacture of caustic soda.
Description of the Related Art
[002] In numerous industrial and individual purposes, chlorine evacuation is often a
challenge and especially in caustic soda manufacturing. Electrolysis is the process of
decomposing a chemical compound into its elements or producing a new compound by
the action of an electrical current. Basically, an electrolyzer is composed of two electrodes
and a separator called a membrane. In the Chlor-alkali industry, primary products of
electrolysis are chlorine, hydrogen, and sodium hydroxide solution (commonly called
“caustic soda” or simply “caustic”). Currently, in the manufacturing of chlor alkali (NaOH)
the electrolyzers are run by people on the basis of hit and trial method which provides
less yield in certain situations.
[003] Commonly in the recent chlor-alkali production plants, an electrolyzer is defined as
a combination of elementary membrane cells. The electrolysis process takes place in
each cell after applying a current. Therefore, the electrolyzer energy consumption plays
a key role in the process. The electrolyzer overall performance is mainly related to each
cell efficiency. It is well known in the art (“A First course in Electrode Processes”, Derek
Pletcher, “Ion Permeable Membranes”, Thomas A. Davis, J. David Genders, Derek
Pletcher), that voltage variations in the membrane cell are generally a result of physical
changes within the cell components.
[004] Schetter Thomas in patent application DE10217694 describes a method for
dynamic determination of the voltage-current characteristic curve of a fuel cell during
operation under different loading conditions. Although this document addresses the
problem of extracting voltage-current linear curve parameters, it doesn't bring a useful
3. method for analyzing these parameters in an industrial scale and relate them to cell
performance and cost associated.
[005] Caustic soda manufacturing process is a very energy intensive process. There
remains a need in the industry to optimize different input parameters to reduce the overall
manufacturing cost. For example, the usage of electricity itself cost around eighty percent
of the production cost. Electricity cost itself is a function of coal mixture, product mixture
and how load is distributed across the electrolyzers.
[006] Accordingly, there remains a need in the art to develop an invention to overcome
the problems imposed by the conventional prior arts and more particularly, to systems,
devices and method to generate a methodical layer by predicting how the electrolyzers
should be run in the product mix. The approaches described in this section are
approaches that could be pursued, but not necessarily approaches that have been
previously conceived or pursued. Therefore, unless otherwise indicated, it should not be
assumed that any of the approaches described in this section qualify as prior art merely
by virtue of their inclusion in this section.
Summary of the Invention
[007] Various embodiments of present invention disclose systems, methods, devices,
and apparatus are provided herein for an Internet of Things (IoT) system configured for
predicting optimal load for which yield is maximum by using multiple input electrolyzer
parameters.
[008] Embodiments of the present invention use swarm optimization algorithm to predict
one or more optimal electrolyzer loads.
Brief Description of the Drawings
These and other features and aspects will become better understood with regard to the
following description and accompanying drawings wherein:
FIG.1 is a screen shot of tabular format of different scenarios illustrating ranking based
on load, in accordance with various embodiments of the present invention;
FIG.2 is a pictorial representation of electrolyser load breakdown in terms of cost of
power, in accordance with various embodiments of the present invention;
4. FIG.3 is a pictorial representation of multiple input parameters of optimization module of
the present system, in accordance with various embodiments of the present invention;
FIG.4 is a pictorial representation of results of AI based process in accordance with
various embodiments of the present invention;
FIG.5 is a pictorial representation of tabular format illustrating recommendation of
electrolysers based on multiple input parameters provided to the AI algorithm for
prediction, in accordance with various embodiments of the present invention; and
FIG.6 is a pictorial representation of product matrix, in accordance with various
embodiments of the present invention;
DETAILED DESCRIPTION OF THE PRESENT INVENTION
[009] Persons of ordinary skill in the art will understand that the present disclosure is
illustrative only and not in any way limiting. Each of the features and teachings disclosed
herein can be utilized separately or in conjunction with other features and teachings to
provide a deployable manufacturing system and method. Representative examples
utilizing many of these additional features and teachings, both separately and in
combination, are described in further detail with reference to the attached figures. This
detailed description is merely intended to teach a person of skill in the art further details
for practicing aspects of the present teachings, and is not intended to limit the scope of
the claims. Therefore, combinations of features disclosed in the detailed description may
not be necessary to practice the teachings in the broadest sense, and are instead taught
merely to describe particularly representative examples of the present teachings.
[0010] Some portions of the detailed descriptions herein are presented in terms of
algorithms and symbolic representations of operations on data bits within a computer
memory. These algorithmic descriptions and representations are the means used by
those skilled in the data processing arts to most effectively convey the substance of their
work to others skilled in the art. An algorithm is here, and generally, conceived to be a
self-consistent sequence of steps leading to a desired result. The steps are those
requiring physical manipulations of physical quantities. Usually, though not necessarily,
these quantities take the form of electrical or magnetic signals capable of being stored,
5. transferred, combined, compared, and otherwise manipulated. It has proven convenient
at times, principally for reasons of common usage, to refer to these signals as bits, values,
elements, symbols, characters, terms, numbers, or the like.
[0011] It should be borne in mind, however, that all of these and similar terms are to be
associated with the appropriate physical quantities, and are merely convenient labels
applied to these quantities. Unless specifically stated otherwise as apparent from the
below discussion, it is appreciated that throughout the description, discussions utilizing
terms such as “processing,” “computing,” “calculating,” “determining,” “displaying,”
“configuring,” or the like, refer to the actions and processes of a computer system, or
similar electronic computing device, that manipulate and transform data represented as
physical (electronic) quantities within the computer system's registers and memories into
other data similarly represented as physical quantities within the computer system
memories or registers or other such information storage, transmission or display devices.
[0012] The headings and Abstract of the Disclosure provided herein are for convenience
only and do not interpret the scope or meaning of the implementations.
[0013] FIG.1 is a screen shot of tabular format 100 of different scenarios illustrating
ranking based on load, in accordance with various embodiments of the present invention.
For example, if the most efficient electrolyzer is run on highest load, it will become the
most inefficient. Therefore, the load allocation across the electrolyzers is a non-trivial
problem.
[0014] FIG.2 is a pictorial representation 200 of electrolyser load breakdown in terms of
cost of power, in accordance with various embodiments of the present invention. The cost
of power is further divided into specific power consumption and per unit power cost.
Moreover, the reason excel model breaks down is because it is complex multi variate high
order polynomial function.
[0015] FIG.3 is a pictorial representation 300 of multiple input parameters of optimization
module of the present system, in accordance with various embodiments of the present
invention.
[0016] Embodiments of the present invention, uses a differential evolution algorithm to
predict multiple optimal electrolyzer loads. The multiple input parameters of optimization
module of the present system are illustrated in pictorial representation 300. However,
6. power source of each eletrolyzer can be changed. Moreover, minimum current density
(CD) and maximum current density (CD) of each eletrolyzer can be set as per local
conditions. The machine learning algorithm takes into account both the minimum current
density (CD) and the maximum current density (CD) to evaluate and predict the optimal
load for which the yield is maximum given the production constraints. The optimizer code
module is configured to evaluate the load of each element and automatically predict how
much electricity should be passed through the electrolysers. In turn, the present invention
is able to save considerable power source required to execute the machinery to get the
end product. The overall cost is considerably reduced with the implementation of the
optimizer code module.
[0017] In some implementations, the machine learning algorithm can comprise utilizing a
swarm optimization algorithm to predict these optimal electrolyzer loads. Examples of the
swarm optimization algorithm include but are not limited to Genetic Algorithms (GA), Ant
Colony Optimization (ACO), Particle Swarm Optimization (PSO), Differential Evolution
(DE), Artificial Bee Colony (ABC), Glowworm Swarm Optimization (GSO), and Cuckoo
Search Algorithm (CSA), Genetic Programming (GP), Evolution Strategy (ES),
Evolutionary Programming (EP), Firefly Algorithm (FA), Bat Algorithm (BA) and Grey Wolf
Optimizer (GWO), or combinations thereof.
[0018] FIG.4 is a pictorial representation 400 of results of AI based process in accordance
with various embodiments of the present invention. FIG.5 is a pictorial representation 500
of tabular format illustrating recommendation of electrolyzers based on multiple input
parameters provided to the AI algorithm for prediction, in accordance with various
embodiments of the present invention and FIG.6 is a pictorial representation 600 of
product matrix, in accordance with various embodiments of the present invention.
[0019] The multiple input parameters can be customized according to product mix taking
into considerations different parameters as illustrated in FIG.6 of the present invention.
[0020] Chlorine evacuation is often a hinderance in caustic soda manufacturing.
Therefore, product balance is a key decision factor. Taking into account storage
capacities at any given point of time, the present modules of the invention is able to
evaluate product mixture in such a way that the evaluations provide maximum profit at
any given point of time for the company.
7. [0021] Embodiments of the present invention, provides analytical module to evaluate and
compare historical input data.
[0022] Various embodiments of the present invention, provides Supervisory Control and
Data Acquisition SCADA (supervisory control and data acquisition) for streamlining the
present system, which is the gathering of data in real time from remote locations in order
to control equipment and conditions.
[0023] The advantage of the present invention is that the system is fed with at least one
electrolyzer parameter which is used to evaluate and predict optimal load for which the
yield is maximum given the production constraints like the raw material availability.
[0024] It will be understood by those skilled in the art that the preferred embodiments are
provided by a combination of hardware and software components, with some components
being implemented by a given function or operation of a hardware or software system,
and many of the data paths illustrated being implemented by data communication within
a computer application or operating system. The structure illustrated is thus provided for
efficiency of teaching the present preferred embodiment. It should be noted that the
present invention can be carried out as a method, can be embodied in a system, a
computer readable medium or an electrical or electro-magnetical signal.
8. ABSTRACT
The present invention provides a method and system for predicting optimal load for which
the yield is maximum by using multiple input electrolyzer parameters. The optimizer code
module is configured to evaluate the load of each element and automatically predict how
much electricity should be passed through the electrolysers.