Tata Innovista is a platform that recognizes innovations across various companies within
the
Group. Tata iQ, in partnership with Tata Steel, got this prestigious award in the Core
Process
Innovations category on 11th September 2020 a novel project aimed to reduce Sticker Breakouts in
the LD shop,
leveraging Machine Learning techniques.
Sticker breakout is a common hazardous phenomenon that plaques the LD continuous casters in
Steel
manufacturing plants. A sticker is a rupture in the solidifying steel shell when it is
passing
through the mold to get cast. If unheeded, it can lead to a breakout – a potentially
hazardous
outcome. To detect formation of stickers within the mold, its wall is embedded with a series
of
thermocouples to register temperature signals within the mold. Sticker forming causes the
temperature signal to fluctuate with a particular signature – captured by thermocouples
within its
vicinity. If a sticker alarm is triggered, the casting process is slowed down to allow the
sticker/rupture in shell sufficient time to heal. While rule based logic aimed to detect the
temperature fluctuation signatures associated with stickers can be successful in eliminating
breakouts largely, however, such logic end up with a high false alarm rate, causing
production to be
affected substantially.
To counter this problem, and make the sticker detection mechanism more pointed and accurate,
Tata iQ
developed a Machine Learning model leveraging Boosting techniques and a lot of innovative
Feature
Engineering. The model was successful in reducing the false positive rate substantially and
at the
same time eliminating false negative rate (undetected sticker leading to a breakout). Such a
balanced model has been effective in helping augment the production substantially through
the last
couple of years since its deployment. The solution is scalable and is thus being evaluated
to be
implemented in other casters across Tata Steel. A paper on this solution – jointly written
between
Tata iQ and Tata Steel - was accepted for presentation in the fifth International Conference
on
Advances in Solidification Processes (ICASP5) and the fifth International Symposium on
Cutting Edge
of Computer Simulation of Solidification, Casting and Refining (CSSCR5) - held as a joint
event in
Salzburg, Austria in June 2019.
Tata AIG have been awarded at The Economic Times Digital Warrior Summit &
Award,
scheduled on March 9, 2021.
Best Disruptive Deployment – AI Based Retention Approach for Private Cars.
Private Car insurance makes up significant part of Tata AIG book and retention rates were low.
An
AI/
ML powered retention strategy was rolled out, which provided a lift of 5% on NOP monthly. A
systematic
approach was applied for monthly Private car retention base by scoring every customer on the
model &
defining strategy based on their behaviour. Based on the model output customers were segmented
&
retention approach was implemented accordingly.
Tata iQ has developed a thermal coal price forecasting solution for Tata Power – to
predict future
prices of specific indices of thermal coal – both in the short-term (1 to 3 months) and
long-term (6
to 12 months) horizon. Leveraging this solution to optimally time the buying of coal
consignments
and
also negotiate better, Tata Power had a better buying strategy and was thus able to cut down
substantially on the annul coal-buying spend. In recognition of the effectiveness of the
price
forecasting solution to help augment their coal-buying strategy, Tata Power awarded Tata iQ
with the
Value Creation award on February 2021 for developing the solution.
Commodity price forecasting is tricky – so many different factors are usually simultaneously
in play
affecting prices of commodities that it is difficult to garner all of them and aggregate
their
effect
on prices in an objective manner. The production, consumption, trade flows, inventory
levels,
regulatory policies, market sentiments, macro-economic factors – all can affect commodity
prices, to
varying degrees which varies across time. Various data sources were leveraged to procure and
collate
all the diverse but relevant data elements that can affect prices of different thermal coal
indices.
The next important hurdle was to establish causality – which of the different data elements
affect
future coal prices, when and by what amount. Different statistical and machine learning
techniques
were employed to categorically assess the different data elements and their causal effect on
the
price
of each coal index. Appropriate time series forecasting models were thus developed – uniting
all the
different data elements to predict how future coal prices of specific thermal indices might
behave
in
the future.
The entire solution is hosted on the cloud, so that it can be accessed by anybody anytime
from
anywhere. However, this required a thorough automation of the entire process – from data
download to
analysis and
identification of the set of variables most important as of today and then use the
shortlisted suite
to develop a forecasting model that is best in terms of accuracy and consistency of
performance. A
highly efficient dashboard to house the entire automated solution has ensured that Tata
Power is
able
to use the solution conveniently, have access to different news articles and insights
affecting
prices
and of course, a self-learning and evolving intelligence sitting at the centre forecasting
prices
and
at the same time continuously learning how to do it better.
Tata iQ received the best paper award in ANQ Congress 2020, which was held in South Korea.
"Asian
Network for Quality (ANQ) consisting of all non-profit organizations in Asia that seek to
improve
quality of human life by contributing to the progress of science and technology; and to the
development of industry through promotional activities for the research and development of
philosophy,
theory, methodology and application in the field of quality and quality management.”
140 research papers were selected from various Asian Countries and our paper was selected as
one of
the best papers. The title of the paper was "Reducing idle freight pay out and carbon
footprint
through application of operations research at Tata Steel India".
This paper talked about the implementation of 3 projects which helped TSL to reduce idle
freight
through better utilization of vehicle/ rake space for FG transportation. There were 2 part to
this
project, the 1st was developing the core optimization model which recommends how to stack FG
in a
vehicle and the 2nd part was a 3D visualization of FG loading in a Vehicle. 3D visualization
give
confidence to the user about authenticity of the recommendation.
Tata Salt was launched in 1983, as the first national branded salt of India. It pioneered salt
iodization in the country,
bringing an iodized vacuum-evaporated salt into a market where unbranded, unpackaged salt was the
norm.
Mithapur plant produce Salt, Soda Ash and Sodium Bicarbonate. With an annual production of 12+ lakh
MT of Salt along with Soda Ash
and Sodium Bicarbonate is transported across India over rail.
Mithapur plant receives 1-2 rakes daily from Indian Railways. Rake are loaded with Salt and Chemical
and dispatched to a destination to meet
demand. Tata Chemicals (TCL) and Tata Consumer Products (TCPL) team used to plan the rake logistics
using excel based tool.
TCL, TCPL and Tata iQ collaborated and developed a Web based tool for rake logistics planning. A
user can upload data and run the model to
get rake plan. The model could be executed multiple times and user can select any of the rake plans
after comparison
The solution consists of a Heuristic based MIP Optimization model built using PYOMO (CBC Solver) and
a web-based UI using Nodejs to generate
a detailed excel based report as part of the solution. Few of the benefit includes automation of
logistic planning, less prone to disruption,
less stock outs and healthily inventory at destination.
It is a quick and easy to use tool. It reduces man-hours required for logistic planning and
consumption scheduling along with an upfront
visibility of inventory status for the entire planning period and comparison of different scenario
i.e. What – If analysis.
Tata Innovista is a platform that recognizes innovations across various companies within the
Group. Tata iQ, in partnership with Tata Steel, was the finalist
in the Tata Invent category on 14th November 2021 a novel project aimed to establish a system for
recommending online casting speed which can be used by all the
Operators to run the caster at optimum casting speed.
Caster speed is governed by SOP speed chart, which has been evolved over a period of 7 years. It
incorporates all the learning from failures in the speed chart
supplied by OEM. Casting process involves multiple/critical variables starting from steel
chemistry/cleanliness/temperature/ladle condition/dynamic parameters like
heat flux/mould level fluctuations/bps etc. Every operator tries to run the caster according to SOP
speed chart taking all the dynamic parameters into account. This
calls for understanding of process stability to run caster at maximum speed by different operators.
This is also true that higher speed requires most stable casting
condition in terms of heat transfer (uniform shell growth), mould level fluctuations & reflection of
uniform heat transfer in thermocouple values in BPS. Currently,
caster speed is conservative due to non-availability of any intelligent solutions or decision-making
engine for operator to run in auto mode.
Casting speed is controlled by operator basis guiding principles (SOP) and experience. To increase
yield and to improve productivity, an intelligent data model
system has been developed to recommend continuous casting speed. Logic is based on SOP parameters
i.e., slab thickness/slab width/superheat and other dynamic process
parameter i.e., bps (breakout prevention system)/heat flux/mould level fluctuations.
Journey of model development started with model selection, correct data availability, server
availability, processing time, offline validation and response.
For model development different level of data was analysed to recommend casting speed with various
machine learning algorithms like KNN (K-nearest neighbour)/RF
(random forest)/XGBoost. In-view of dynamic operating regime of casting from different operator
based on their experience and understanding of stable casting
condition for same set of parameters, it was difficult to predict recommended speed. Being a
subjective operational task, a heuristic data model was built which
recommends casting speed taking all the dynamic parameters in consideration. Model reads the 60 data
points (rolling data) captured at every 2 second and process
the same using logical algorithm which satisfies approx. 40 logics before recommending casting speed
at an interval of 5 sec. Whenever there is a violation in terms
of dynamic operating condition, it will raise a flag resulting in decrease of recommended casting
speed.
This invention is a real-time system for recommending casting speed which takes care of all the
dynamic casting conditions, so that all operators can run the
Caster at optimum casting speed. It is a part of multiple system strategy for productivity
improvement and operates independently. The solution is scalable and is
thus being evaluated to be implemented in other casters across Tata Steel.
Coal price constitutes 70% of Power Generation cost. The innovation was developed to reduce coal
cost. To reduce generation cost, Tata Power adopted following
approaches.
a) Coal market analysis is being done through analysing different international subscriptions like
Platts, IHS, Argus reports etc. Along with the analysis,
the Coal Price Predictor tool helped in arriving critical management decision of sourcing.
b) Generation Planning: Ensures envisaging changes in future power demand considering plant load
factor, outages requirement.
c) Coal Planning: The objective is to minimize inventory carrying cost in accordance to estimated
demand-supply of coal that is done by optimizing number of
shipments required.
d) Coal blending: Mixing of different grades of coal through blend which is done by MSR Tool.
Optimum blend is calculated by identifying alternate fuel specs,
price, generation plan, stock, unit performance etc.
e) Surrender prediction: With historical data and estimation of installed power generation capacity
of the western region, this tool estimates capacity which
is excess in comparison with future demand.
To have a “Pit to Plant” solution, the Web Based MSR tool has integrated with AI based Price
Predictor Tool which on one hand gives optimum blend ratio and also
gives forecast on sourcing dynamics. This AI based Pit to Plant solution of coal sourcing is the
first of its kind in private or public power utility.
The solution connects all of the above into a single streamlined process housed across two web-based
tools. This innovation has served the purpose of not only
reducing coal cost but also ensured optimum blend of different off-spec coal. Optimum blend results
into better heat rate, thereby increasing plant efficiency.
Thus, with reduced cost and improved plant efficiency, this innovation has helped in lowering
generation cost.
Being able to determine the sensitivity of coal prices to specific external factors through due
analysis - which keep changing on a dynamic basis - is key to
both accuracy as well as consistency. Tata iQ’s innovative solution aims to integrate the
simultaneous influences of a lot of different factors and identify
lead and lag causality of different factors with one another, wherever present. Owing to the dynamic
nature of external factors which govern prices, it was
also essential that the evaluation of causal elements be done on a regular basis, that is the model
could not be static but a self-learning one – which is able
to attenuate its predictors based on the current regime and primary influence factors.
Tata iQ has been recognized as one of Asia’s Most Admired Brands by White Page International at their 10th Leadership Conclave held on August 2022. White Page International is a global consulting firm with a diverse portfolio that includes Brand Marketing, Research, Advisory & Consulting, Large Scale Generic & Customized Conferences, Publishing, and Digital and Television Content. Their Business Conferences honour the best brands and leaders across different Asian countries and host global speakers and forum discussions on important global business issues.
The Conclave was attended by over 220 CEOs and CXOs from India, Kuwait, United Arab Emirates, Singapore, Malaysia, Bangladesh, United Kingdom, Myanmar and Africa. White Page International also unveiled the annual listing of Asia's 100 Power Leaders in Marketing & Communications, Human Resources, Finance & Technology.
We are also very delighted that our Chief People Officer and Business Solution Evangelist, Amit Sachdev has been recognised as one of Asia’s 100 Power Leaders in Human Resources. Amit contributes to our organisation’s success by building and implementing progressive people policies, processes and practices which result in Talent Attraction – Growth – Development – Retention.
We are honoured by the recognitions motivating us along the way. We aim to remain focused on continuously raising the bar for ourselves and working towards excellence in our role as the data and analytics centre for our Group companies.
Tata Innovista is a platform that recognizes innovations across various companies within the Group. Tata iQ, in partnership with Tata Steel, was the finalist in the event held on 20th July 2022, in the Tata Invent Category. The project is a novel one, aimed at detecting and measuring the size distribution and trends of the pallets in the Greenball Pallet Plant.
The solution automates the process of measuring the size distribution of the Greenball pallet using high speed cameras and a computer vision deep learning model. It provides real-time inputs to the machine for adjustment of the parameters for optimal size of pallet required for the blast furnace. The automation of the process not only provides these inputs in real-time but is also more accurate as the detection of the pallets are above 98%, critical for this continuous process.