This diploma thesis deals with a proposal how to improve technology of mainte-nance of trucks and buses of ICOM transport branch in Humpolec. Main aim of this diploma thesis is the analysis of current technology of maintenance, especially the oil system and it´s modification. This aim was reached by suggestion of the new technol-ogy of oil system, technical eguipment and elaboration of new technical methods. Modern and efficient technology of oil system for trucking and repairation is the solution of this topic. That is the set of processes with operating system (monitoring) whitch guarantees safe, enviroment storage of oils, greases and antifreezer, their de-cantation and precise dosing during distribuion.

This thesis focuses on the development of a health monitoring system for gearbox transmissions. This was accomplished by developing and understanding a two-stage gearbox computer model that emulates an actual gearbox test rig. The computer model contains actual gearbox geometry, flexible shafts, bearings, gear contact forces, input motor torque, output brake torque, and realistic gearbox imbalance. The gear contact force of each gear stage and the input bearing translational acceleration were the main outputs compared between a healthy gearbox and damaged gearbox computer model. The damage of focus was a fatigue crack on the input pinion gear. A sideband energy ratio comparison yielded the computer simulation accurately modeled the difference between a healthy and damaged gearbox. The next step in this study involved the development of a repeatable procedure to initiate and propagate a fatigue crack at the tooth root in an actual spur gear. A damaged spur gear allows for a future comparison of an actual healthy and damaged gearbox system in the lab. A custom fatigue fixture was designed and manufactured for a Martin S1224BS 1 spur gear. The fatigue crack was initiated by position control fatigue testing which deflects the gear tooth a set amplitude for a number of cycles. Over the length of the test, the load that the tooth can withstand in bending decreases as damage begins to occur. Once the max load on the gear has dropped by a significant percentage (5-15%) a crack has initiated and begun to propagate across the tooth face. The use of a scanning electron microscope confirmed the presence a fatigue crack.

This dissertation develops systems engineering and machine learning models for aviation maintenance support. With the constant increase in demand for air travel, aviation organizations compete to maintain airworthy aircraft to ensure the safety of passengers. Given the importance of aircraft safety, the aviation sector constantly needs technologies to enhance the maintenance experience, ensure system safety, and limit aircraft downtime. Based on the current literature, the aviation maintenance sector still relies on outdated technologies to maintain aircraft maintenance documentation, including paper-based technical orders. Aviation maintenance documentation contains a mixture of structured and unstructured technical text, mainly inputted by operators, making them prone to error, misunderstanding communication, and inconsistency. This dissertation intends to develop decision support models based on systems engineering and artificial intelligence models that can automate the maintenance documentation system, extract useful information from maintenance work orders, and predict the aircraft's top degrader signals based on textual data. The first chapter of this dissertation introduces the significant setbacks of the aviation industry and provides a working ground for the following chapters. The dissertation's second chapter develops a system engineering framework using model-based systems engineering (MBSE) methodology to model the aviation maintenance process using the systems engineering language (SysML). The outcome of this framework is the design of an automated maintenance system model that can be used to automate maintenance documentation, making it less prone to error. The third chapter of the dissertation uses textual data in maintenance work orders to develop a hybrid approach that uses natural language processing (NLP) and transformer models to predict the readiness of a legacy aircraft. The model was tested using a real-life case study of the EA-6B military aircraft. The fourth chapter of this dissertation develops an ensemble transformer model based on three different transformer models. The ensemble model leverages the benefits of three different transformer architectures and is used to classify events based on an aviation log-based dataset. This dissertation's final and fifth chapter summarizes key findings, proposes future work directions, and provides the dissertation's limitations.