Lidé na fakultě
Ing. Martin Kála, Ph.D.

2022, Transportation Research Procedia, Amsterdam, Elsevier B.V.), p. 238-245), ISSN 2352-1457

Aircraft maintenance at the technical base includes both scheduled and unscheduled repairs. When performing repairs, there are detailed inspections of aircraft, which are ordered in advance by the customer. During these inspections, it is possible to detect other unsatisfactory condition of the aircraft in terms of continuing airworthiness, which needs to be corrected. These unplanned failures are findings and are entered into the maintenance organization's system, which is required to keep records of activities performed on the aircraft. Finding descriptions are created by technicians and are usually stored as unstructured text that does not allow subsequent analysis with a database of such records. The presented work performs automatic text analysis of findings using a dedicated software tool. For the purpose of the analysis, a lexicon was created, with components and failures appearing in maintenance records. The lexicon was used in automatic text analysis, where the output was a statistic of the most frequent components and failures in the stored maintenance data. This statistic can be used for maintenance planning optimization and better prediction of unscheduled repairs.

Stať ve sborníku z prestižní konf. (Scopus)

2022, 2022 New Trends in Civil Aviation (NTCA), Praha, České vysoké učení technické v Praze), p. 35-41), ISBN 978-80-01-06985-1, ISSN 2694-7854

The aim is to provide a method of predicting the material required for heavy aircraft maintenance using mathematical prediction models. This includes the possibility of comparing the accuracy of different models. Previous studies have not applied multiple different mathematical prediction models to real operational data, i.e., data from an Approved Maintenance Organisation (AMO). To easily operate and display the results, computer software, including a Graphical User Interface (GUI), has been developed in a MATLAB environment. Real operational data was provided by AMO organisation for the years 2016 to 2020 inclusive. A total of ten mathematical prediction models were selected for the prediction calculations. These were selected based on research and previous studies on the topic of material prediction. The user of the software has the possibility to perform the prediction for all parts in the database or only for one specific part. The results are stored in the database or displayed directly in the GUI. The model accuracies for all parts are on average about 92 %. If we use cleaned data and exclude from the predictions parts that often have zero quarterly demand, we get to an average prediction accuracy of 83 %. The most accurate forecasts are made by the Exponential Smoothing with use of Moving Average Forecasting Model, Croston's Forecasting Model and Syntetos-Boylan Approximation Forecasting Method models.

Stať ve sborníku z prestižní konf.

2020, Transportation Research Procedia, Linz, Elsevier BV), p. 46-55), ISSN 2352-1465

This study was aimed to find a way how to deal with hardly predictable circumstances while performing routine access works during aircraft heavy maintenance and to estimate the time spent with the work. The lack of maintenance data was crucial in dealing with this issue, therefore, additional measurements were necessary. For this purpose, this study was done in cooperation with Czech Airlines Technics Maintenance Repair Organization. The company currently estimates timing of panel manipulation based on the information contained in the manufacturer’s documentation. A database was established with work measurements of maintenance technicians accessing panels during real aircraft maintenance. They should by their nature reflect complications arising during the access panel manipulation and of the specific operational factors in the company. The main importance of the database lies in the creation of additional data to refine the aircraft maintenance planning estimates. Based on the measurements, it was possible to demonstrate that the access panel manipulation times as stated in the manufacturer’s documentation are only indicative. For each measurement performed, the measured overall time of panel manipulation was much higher than the equivalent time estimates by the manufacturer. During the measurements, several other factors were also discovered as causal to differences in the manipulation times. The database served as the basis for a developed software tool providing more accurate estimates of access panel manipulation times and resulting in more accurate estimates in maintenance planning in the Czech Airlines Technics, although the results are well reusable with other Maintenance Repair Organizations.

Stať ve sborníku z prestižní konf. (Scopus)

2019, TRANSPORT MEANS 2019 - PROCEEDINGS OF THE 23rd INTERNATIONAL SCIENTIFIC CONFERENCE, Kaunas, Kaunas University of Technology), p. 1218-1222), ISSN 1822-296X

Modern airlines strive to satisfy customer requirements to the highest extent possible, continuously searching for advantages of modern technologies that could be used for the purpose. Another motivation may be the willingness to improve overall operations effectiveness while possibly reducing costs of each flight. In this regard, WiFi modification and cabin reconfiguration are common tasks in today aviation world. These are one of the typical examples of the current aircraft upgrades demanded by airlines to better meet customer requirements but from the perspective of a maintenance organization, this is often a challenging task. With respect to that, this article describes how turnaround time of cabin and WiFi modification can be improved during base maintenance visits in MROs, the Maintenance Repair and Overhaul organizations. This improvement was verified with the Czech Airlines Technics, one of the famous MROs in Europe. The main points of success are correct understanding of human factors, implementation of maintenance planning, Gantt charts and also application of modern approach to workflow in the MRO itself. Once implemented, turnaround time of these complex maintenance visits can be shortened by days. The airliners highly appreciate this fact and it also enables the MRO to achieve more hangar space during maintenance season.

Stať ve sborníku z prestižní konf. (Scopus)

2019, Proceedings of 2019 International Conference on Military Technologies (ICMT), Brno, Univerzita Obrany), ISBN 978-1-7281-4593-8

Maintenance planning and calculation of maintenance turnaround time require consideration of many influences. This leads to the calculated turnaround time usually not being precise. This paper deals with the time estimation of unscheduled works which may occur during maintenance of an aircraft and which can lead to financial losses or reduced usability of the aircraft for flying missions due to extended stay in a hangar bay. The main assumption is that there exists dependence between unscheduled works and predictors known prior to the maintenance. Two methods were considered to estimate the turnaround time, namely maximum likelihood estimation and Bayesian regression. The study was done in cooperation with Czech Airlines Technics company which provided necessary data from aircraft maintenance. The results indicate that, given the data normally available, only the model based on maximum likelihood estimation managed to reproduce reality when proposed for each aircraft type individually. The model was validated in the Czech Airlines Technics company and implemented into software environment.

Stať ve sborníku z prestižní konf. (Scopus)