This project will develop a prototype smart hy-rail wheel system for detection of certain classes of geometry defects using low coast inertial systems at the wheel. Work in Stage 1 will focus on sourcing, acquiring, and assembling the hardware necessary for the prototype design, as well as generating the initial data needed for work in Stage 2. Sensors will be acquired, and mounting brackets will be fabricated. Powering source and location for testing will be determined. Laboratory testing of hardware will be performed, and data acquisition will be validated. The system will be installed on hy-rail and 100+ miles of data will be collected working with industry partners. Inspection system data will be gathered from the inspection vehicle. This will be done on two separate trips for two different classes of railways. Exploratory data analysis will be performed and appropriate filter and data decomposition techniques (FFT, HHT, etc.) will be determined. Base statistical summaries and correlations of IMU data and inspection system data will be determined. In Stage 2, the machine learning AI will be developed based on the IMU data and inspection system data. The system will be trained using the data acquired in Stage 1, with the goal of the prototype system being able to detect defined classes of geometry defects. An AI interface will be developed using functional networks based on the filtered and decomposed data from Stage 1 work. The focus of the AI interface will be a subset of geometry parameters as defined in the proposal using 70% of the data available. : Validation will be performed on the remaining 30% of the data by exercising the model developed in this work and developing a validation matrix for various parameters and level of condition. Detailed design of commercially viable prototype that includes integration, data communications and mobile app reporting. The final report will include all relevant data, methods, models, and conclusions. Guidelines for using the system by the railroad entities will also be provided in the final report