MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202611001510 A) filed by Ajaz Husain Warsi; Dr. Hamza Siddiqui; Dr. Archana Sachindeo Maurya; Minhajul Arfeen; Dr. Md Ibrahim; Aqsa Fatima; Anamika Sharma; Akanksha Singh; Nitika Gupta; and Atul Verma, Dashauli, Uttar Pradesh, on Jan. 6, for 'ai and machine learning-assisted structural engineering of perovskite solar cells to improve energy efficiency.'
Inventor(s) include Ajaz Husain Warsi; Dr. Hamza Siddiqui; Dr. Archana Sachindeo Maurya; Minhajul Arfeen; Dr. Md Ibrahim; Aqsa Fatima; Anamika Sharma; Akanksha Singh; Nitika Gupta; and Atul Verma.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "A method for artificial intelligence (AI) and machine learning (ML)-assisted structural engineering of perovskite solar cells to improve energy efficiency, comprising: (a) acquiring material data, structural data, and fabrication process data associated with perovskite solar cells; (b) preprocessing the acquired data to extract performance-related features using normalization, filtering, dimensionality reduction, and feature engineering techniques; (c) training one or more AI and machine learning models to learn relationships between the extracted features and photovoltaic performance parameters; (d) generating optimized structural configurations of the perovskite solar cells using the trained models; (e) validating the optimized structural configurations through physics-based simulation, experimental evaluation, or a combination thereof; and (f) fabricating perovskite solar cells based on the validated optimized structural configurations, whereby energy conversion efficiency and operational stability of the perovskite solar cells are improved. Dependent Method Claims 2. The method as claimed in claim 1, wherein the AI and machine learning models comprise supervised learning models, unsupervised learning models, reinforcement learning models, generative learning models, or combinations thereof. 3. The method as claimed in claim 1, wherein the performance-related features include bandgap energy, grain size distribution, defect density, carrier lifetime, diffusion length, interfacial band alignment, and thermal stability indicators. 4. The method as claimed in claim 1, wherein the optimized structural configurations include absorber layer morphology, crystal orientation, layer thickness, interface alignment, and charge transport pathways. 5. The method as claimed in claim 1, wherein reinforcement learning dynamically optimizes fabrication parameters including deposition conditions, solvent composition, annealing temperature, annealing duration, and interface treatment conditions. 6. The method as claimed in claim 1, wherein the validation step comprises drift-diffusion simulations, optical absorption modeling, thermal simulations, or charge transport and recombination modeling. 7. The method as claimed in claim 1, further comprising continuously updating the AI and machine learning models using performance feedback obtained from fabricated perovskite solar cells. 8. The method as claimed in claim 1, wherein the method supports optimization across laboratory-scale research, pilot-scale manufacturing, and industrial-scale fabrication environments. Independent System Claim 9.A system for AI-assisted structural optimization of perovskite solar cells, comprising: (a) a data acquisition module configured to collect material, structural, fabrication, and performance data; (b) a preprocessing and feature engineering module configured to process the collected data; (c) an AI and machine learning engine configured to predict photovoltaic performance and generate optimized structural configurations; (d) a simulation and validation module configured to evaluate the optimized configurations; and (e) a fabrication control module configured to implement validated configurations during solar cell fabrication. Dependent System Claims 10. The system as claimed in claim 9, wherein the AI and machine learning engine comprises deep neural networks, convolutional neural networks, recurrent neural networks, long short-term memory networks, autoencoders, graph neural networks, or ensemble learning models."
Disclaimer: Curated by HT Syndication.
