Technology

Designing a better cement clinker

Published

9 years ago

December 31, 2016

admin

Panyam Cements from Andhra Pradesh has implemented a non-linear model to formulate a better clinker composition. Sreekanth Sajjala recounts the results obtained with non-linear modelling.

Designing a better or a different clinker is a time-consuming effort. Right from the raw mix, the coal and the operating parameters of the kiln have to be changed. Often, this can impact the sta-ble running of the kiln which becomes very expensive in terms of fuel consumption and sub-optimal production.

Assessing a new clinker is also not instant, it takes 28 days for all the strengths to be measured. This means that all in all, it takes about two-three months to design and evaluate a new clinker composition. There currently are no accurate prediction methods as the formation of clinker and the link between its material properties and chemical composition are not linear. Machine learning is a field of study that gives computers the ability to learn without being explicitly programmed. Computers are not programmed but are expected to identify patterns and thereby build a model which can generate repeatable results.

These patterns need not be linear or direct, which means that machine learning methods are ex-tremely well suited in the prediction of cement properties.

Our Scenario
Our clinker had excellent 28-day strengths (680-700) and relatively lower 1-day strengths (140-160); this meant that our customers were disappointed by our PSC where the addition of GGBS (a material with a low heat of hydration) further lowered the 1-day strengths. This meant that we couldn’t mix more than 45 per cent GGBS in PSC though up to 60 per cent was allowed. We needed a clinker which would have higher initial strengths and quickly, as the opportunity cost was quite high. We, in the R&D division, turned to non-linear modeling to design the chemical composition of a clinker that would have up to 50 per cent higher initial strengths.

The most important thing in non-linear modeling was the availability of reliable data and a lot of it. Though our lab maintained immaculate records of both chemical and physical aspects of clinker, they were all in physical form. We digitised over 18 months’ worth of clinker data. Over 500 records were used as the training set. The surface area and percentage of gypsum were not taken into account, as all the lab samples were ground evenly and had the same amount of gyp-sum.

The Method
A neural network with four hidden layers was used with a hyperbolic tangent activation func-tion. Neural networks are computer systems modeled on the human brain and nervous system. They are used mainly for non-linear modeling and computer vision. Each node is assigned a weight with which the incoming input matrix is multiplied by. These weights are assigned during training where back propagation and other training methods are used with the training set. The model is then validated on a smaller separate dataset called the testing set.

The results
When the directional output was plotted with the various variables, the optimal composition was realised for higher initial strengths. We were able to formulate a viable clinker with over 50 per cent higher 1-day strength and 10 per cent lower 28-day strength. The next step was to design a model which could predict the kiln’s output chemical composition on the basis of the raw meal chemical composition, coal consumption and the operating parameters. We believe this could help us match the raw mix and coal more optimally and help us preserve coal and high grade limestone. One thing non-linear modeling can do which linear modeling cannot do, is factor in the indirect impact of trace compounds like MgO. Non-linear models, by observing correlations, can link trace elects to the indirect effects like their function in the formation of major com-pounds. This model has helped us increase how much GGBS we add in our PSC and has contributed to great cost savings through clinker conservation.

About the author
Sreekanth Sajjala is a part of the R&D team at Panyam Cements, Andhra Pradesh. He is one of the main contributors to the model Panyam has developed to predict the strength of clinker on the basis of its chemical composition.

Technology

ARAPL Reports 175% EBITDA Growth, Expands Global Robotics Footprint

Affordable Robotic & Automation posts strong Q2 and H1 FY26 results driven by innovation and overseas orders

Published

2 months ago

October 15, 2025

admin

Affordable Robotic & Automation Limited (ARAPL), India’s first listed robotics firm and a pioneer in industrial automation and smart robotic solutions, has reported robust financial results for the second quarter and half year ended September 30, 2025.
The company achieved a 175 per cent year-on-year rise in standalone EBITDA and strong revenue growth across its automation and robotics segments. The Board of Directors approved the unaudited financial results on October 10, 2025.

Key Highlights – Q2 FY2026
• Strong momentum across core automation and robotics divisions
• Secured the first order for the Atlas AC2000, an autonomous truck loading and unloading forklift, from a leading US logistics player
• Rebranded its RaaS product line as Humro (Human + Robot), symbolising collaborative automation between people and machines
• Expanded its Humro range in global warehouse automation markets
• Continued investment in deep-tech innovations, including AI-based route optimisation, autonomy kits, vehicle controllers, and digital twins
Global Milestone: First Atlas AC2000 Order in the US

ARAPL’s US-based subsidiary, ARAPL RaaS (Humro), received its first order for the next-generation Atlas AC2000 autonomous forklift from a leading logistics company. Following successful prototype trials, the client placed an order for two robots valued at Rs 36 million under a three-year lease. The project opens opportunities for scaling up to 15–16 robots per site across 15 US warehouses within two years.
The product addresses an untapped market of 10 million loading docks across 21,000 warehouses in the US, positioning ARAPL for exponential growth.

Financial Performance – Q2 FY2026 (Standalone)
Net Revenue: Rs 25.7587 million, up 37 per cent quarter-on-quarter
EBITDA: Rs 5.9632 million, up 396 per cent QoQ
Profit Before Tax: Rs 4.3808 million, compared to a Rs 360.46 lakh loss in Q1
Profit After Tax: Rs 4.1854 lakh, representing 216 per cent QoQ growth
On a half-year basis, ARAPL reported a 175 per cent rise in EBITDA and returned to profitability with Rs 58.08 lakh PAT, highlighting strong operational efficiency and improved contribution from core businesses.
Consolidated Performance – Q2 FY2026
Net Revenue: Rs 29.566 million, up 57% QoQ
EBITDA: Rs 6.2608 million, up 418 per cent QoQ
Profit After Tax: Rs 4.5672 million, marking a 224 per cent QoQ improvement

Milind Padole, Managing Director, ARAPL said, “Our Q2 results reflect the success of our innovation-led growth strategy and the growing global confidence in ARAPL’s technology. The Atlas AC2000 order marks a defining milestone that validates our engineering strength and accelerates our global expansion. With a healthy order book and continued investment in AI and autonomous systems, ARAPL is positioned to lead the next phase of intelligent industrial transformation.”
Founded in 2005 and headquartered in Pune, Affordable Robotic & Automation Ltd (ARAPL) delivers turnkey robotic and automation solutions across automotive, general manufacturing, and government sectors. Its offerings include robotic welding, automated inspection, assembly automation, automated parking systems, and autonomous driverless forklifts.
ARAPL operates five advanced plants in Pune spanning 350,000 sq ft, supported by over 400 engineers in India and seven team members in the US. The company also maintains facilities in North Carolina and California, and service centres in Faridabad, Mumbai, and San Francisco.

Technology

M.E. Energy Bags Rs 490 Mn Order for Waste Heat Recovery Project

Second major EPC contract from Ferro Alloys sector strengthens company’s growth

Published

2 months ago

October 15, 2025

admin

M.E. Energy Pvt Ltd, a wholly owned subsidiary of Kilburn Engineering Ltd and a leading Indian engineering company specialising in energy recovery and cost reduction, has secured its second consecutive major order worth Rs 490 million in the Ferro Alloys sector. The order covers the Engineering, Procurement and Construction (EPC) of a 12 MW Waste Heat Recovery Based Power Plant (WHRPP).

This repeat order underscores the Ferro Alloys industry’s confidence in M.E. Energy’s expertise in delivering efficient and sustainable energy solutions for high-temperature process industries. The project aims to enhance energy efficiency and reduce carbon emissions by converting waste heat into clean power.

“Securing another project in the Ferro Alloys segment reinforces our strong technical credibility. It’s a proud moment as we continue helping our clients achieve sustainability and cost efficiency through innovative waste heat recovery systems,” said K. Vijaysanker Kartha, Managing Director, M.E. Energy Pvt Ltd.

“M.E. Energy’s expansion into sectors such as cement and ferro alloys is yielding solid results. We remain confident of sustained success as we deepen our presence in steel and carbon black industries. These achievements reaffirm our focus on innovation, technology, and energy efficiency,” added Amritanshu Khaitan, Director, Kilburn Engineering Ltd

With this latest order, M.E. Energy has already surpassed its total external order bookings from the previous financial year, recording Rs 138 crore so far in FY26. The company anticipates further growth in the second half, supported by a robust project pipeline and the rising adoption of waste heat recovery technologies across industries.

The development marks continued momentum towards FY27, strengthening M.E. Energy’s position as a leading player in industrial energy optimisation.

Technology

NTPC Green Energy Partners with Japan’s ENEOS for Green Fuel Exports

NGEL signs MoU with ENEOS to supply green methanol and hydrogen derivatives

Published

2 months ago

October 15, 2025

admin

NTPC Green Energy Limited (NGEL), a subsidiary of NTPC Limited, has signed a Memorandum of Understanding (MoU) with Japan’s ENEOS Corporation to explore a potential agreement for the supply of green methanol and hydrogen derivative products.

The MoU was exchanged on 10 October 2025 during the World Expo 2025 in Osaka, Japan. It marks a major step towards global collaboration in clean energy and decarbonisation.
The partnership centres on NGEL’s upcoming Green Hydrogen Hub at Pudimadaka in Andhra Pradesh. Spread across 1,200 acres, the integrated facility is being developed for large-scale green chemical production and exports.

By aligning ENEOS’s demand for hydrogen derivatives with NGEL’s renewable energy initiatives, the collaboration aims to accelerate low-carbon energy transitions. It also supports NGEL’s target of achieving a 60 GW renewable energy portfolio by 2032, reinforcing its commitment to India’s green energy ambitions and the global net-zero agenda.