MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122492 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy University; Malla Reddy Engineering College For Women; Malla Reddy College Of Engineering And Technology; and Malla Reddy Vishwavidyapeeth, Medchal-Malkajgiri, Telangana, on Dec. 5, 2025, for 'ai-driven predictive maintenance unit for high-vibration machinery.'
Inventor(s) include Dr. S. Udaya Bhaskar; Dr. M. Sirisha; Ms. Nagamahesh Vemula; V. Kiran Kumar; Mamidishetti Alekya; and Mr. P. Balaji Krushna.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The behavior of machinery subjected to high-vibration conditions in the manufacturing, mining, transportation, and heavy mechanical industries has been characterized by a faster rate of wear, unexpected failures, and reduced service life. The traditional maintenance methods, which were based on regular inspections and repair responses to incidents, often cause significant aspects of downtimes and inability to avoid safety risks. The present manuscript gives a proposal of an AI-based predictive maintenance unit targeted at high-vibration machine to detect faults in real time, monitor performance, and predict a potential machine failure based on the trends of vibration, wear, and working model. The unit continuously gathers data regarding imbedded vibration sensors, acoustic sensors, temperature sensors and rotational speed sensors. The analysis then makes use of advanced signal-processing methods along with machine-learning-based feature extraction, and, thus, allows identifying anomalous patterns with accuracy. When potential faults are observed, the system sends alerts that include degrees of importance and approximate time-to-failure, so that the maintenance staff can establish corrective actions in terms of promptness. In addition, the technology can be used to make adaptive maintenance schedules, which will take advantage of previous performance and wear usage to schedule efficient service intervals, thereby lowering operational costs and increasing reliability. Connection with the existing machinery can be realized through a modular interface, which eliminates the need to make significant changes to the hardware. The system works in real-time and offline diagnostic and is not only capable of remote monitoring with pre-established industrial communication protocols. In combination, the suggested strategy provides a robust, statistically-grounded model that is expected to reduce unplanned failures, as well as increase the snake machine life span. This type of methodology is particularly beneficial in systems that present high-risk scenarios related to equipment failure like heavy manufacturing, aerospace systems, oil refineries marine propulsion units and automated assembly lines."
Disclaimer: Curated by HT Syndication.
