Intellectual Property India Publishes Patent Application for 'A Method For The Rapid Estimation Of Manganese Content In Manganese Ore Using Mid-Infrared FTIR Spectral Data Analysis And A Multi-Model Machine Learning Framework' Filed by Indian Institute Of Technology (Indian School Of Mines, Dhanbad)

MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202531116056 A) filed by Indian Institute Of Technology (Indian School Of Mines, Dhanbad), Dhanbad, Jharkhand, on Nov. 24, 2025, for 'a method for the rapid estimation of manganese content in manganese ore using mid-infrared ftir spectral data analysis and a multi-model machine learning framework.'

Inventor(s) include Anup Krishna Prasad; Shailayee Mukherjee; Bitan Purkait; Nirasindhu Desinayak; Rachna Rakesh; Ayesha Nayak; Tathastu Das; Arya Vinod; Atul Kumar Varma; Bhabesh Chandra Sarkar; Suren Nayak; and Dhirendra Pratap Singh.

The application for the patent was published on Jan. 9, under issue no. 02/2026.

According to the abstract released by the Intellectual Property India: "A system and method of rapid estimation of manganese content in manganese ore using mid-infrared FTIR spectral data analysis and a multi-model machine learning framework. The present invention is a method to predict manganese content in manganese ore. Manganese ore samples from manganese deposit (204) and ore samples of unknown manganese content (206) are collected; processed and prepared (208) for FTIR analysis (210) and x-ray fluorescence (XRF) analysis (212) as reference (MnXRF, wt%) (214). Samples are processed and prepared at a known dilution factor (216), according to concentration increment for mid-infrared Fourier transform infrared spectroscopy analysis (218) and the resulting spectral signature for all samples (ore sample + KBr) between 4000 to 350 cm-1 are recorded (220). K-fold cross-validation of the ore samples (222) is used to split the sample into training (224) and test sets (226). A data analyzer (230) is used to conduct the analysis using multiple regression models to analyze the selected data. Seven regression models used and multi-model estimation done with average of best three models (230). The training set is used to predict the manganese content, using FTIR data (234). The predicted and observed manganese content in manganese ore samples are compared (238) to prove that the observed and predicted manganese of ore samples are statistically similar (240). The methodology yields manganese content in manganese ore samples (242)."

Disclaimer: Curated by HT Syndication.