|
|
Predictive maintenance with wireless data transfer
Pernica, Michal ; Najman, Jan (referee) ; Dobossy, Barnabás (advisor)
This thesis deals with predictive maintenance and the use of NB-IoT network for its purpose. In the first part of the thesis, the wireless technologies for data transmission are presented, followed by a description of the different types of communication protocols, and lastly, the process of developing predictive maintenance is described. In the second part of the thesis, a server application for predictive maintenance purposes is presented, system control using a microcontroller, the NB-IoT module SIM700E is introduced along with its specifications, connection to the NB-IoT network and implementation of the MQTT protocol. Also, the server software composed of the MQTT broker, Node-Red, Influx DB and Grafana is described. The third section describes the application of predictive maintenance on two devices, namely a thermal chamber and a pneustand. The function of these systems is described, followed by the modifications applied. Afterwards, the fault conditions we want to detect are mentioned and then classifiers are trained to determine the condition. Finally, the control of the systems is redesigned so that it can be done using a microcontroller. Finally, experiments are performed while operating the device and verifying the functionality of predictive maintenance to identify the condition.
|
|
|
Modern approaches to maintenance in engineering practice
Jiroušek, Lukáš ; Konečný, Antonín (referee) ; Hammer, Miloš (advisor)
The thesis deals with maintenance and implementation of modern maintenance approaches in engineering practice. The present thesis focuses on Total Productive Maintenance (TPM). The first part of the thesis defines the general characteristics of maintenance, its division, including an analysis of maintenance types. In the context of maintenance according to the technical condition, the methods of technical diagnostics such as vibrodiagnostics, thermodiagnostics, tribodiagnostics and acoustic diagnostics are also introduced. The second part of the thesis focuses on the philosophy and description of Total Productive Maintenance (TPM) including the individual pillars and the evaluation of Overall Equipment Effectiveness (OEE). The third part deals with the actual practical implementation of TPM at Schaeffler Production CZ s.r.o, with emphasis on autonomous maintenance, e-maintenance and the 7S concept. The final part of the thesis summarizes the benefits and advantages that can be observed by implementing the TPM method in Schaeffler Production CZ s.r.o.
|
|
|
Data Analysis for Predictive Maintenance of a Robotic Arm
Žitný, Roland ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The Mitsubishi MELFA robotic arms used in modern factories work almost without interruption and produce sensory data about their operation. Various analysis techniques can be applied to such data for predictive maintenance, which provide information on the condition and maintenance needs of such robotic arms. The proposed predictive maintenance process consists of a sensory data acquisition system using the slmpclient and mitsubishi-monitor libraries, an analysis method system with anomaly detection using a convolutional autoencoder, anomaly classification using convolutional neural networks, and data segmentation into segments of individual robot actions using hidden Markov models. Such analysis techniques provide information on the severity, type, and location of emerging faults and abnormalities in behavior, which then determine the time required to perform the required maintenance. This work presents a created chain of predictive maintenance processes, where the obtained findings provide valuable insights into the application of predictive maintenance of Mitsubishi MELFA robotic arms in an industrial environment.
|
|
|
Applications of Machine Learning in Predictive Maintenance of Industry 4.0
Navrátil, Tadeáš ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
The thesis develops machine learning algorithms for use in the Industry 4.0 concept. The main focus is on predictive maintenance and visual inspection. In the theoretical part, the thesis focuses on a literature search of machine learning methods in the field of anomaly detection in time series and image data. The practical part deals with the reimplementation of the selected methods and their evaluation using the confusion matrix and metrics based on it
|
|
|
Automatic detection of tool fracture in metal sheet punching
Kluz, Jan ; Rajchl, Matej (referee) ; Brablc, Martin (advisor)
This Bachelor thesis deals with the design and subsequent implementation of the realtime fault detection system during the sheet metal punching process with a tool of small dimensions (0.5 × 12 mm). The proposed system is important for significant ease of the operator's work, acceleration of the process of production, as well as saving of the company finance budget. The first part of this thesis deals with the theoretical background of the studied issue. The following part is a brief theoretical introduction to the field of digital signal processing. The next chapter presents methods developed for fault signals detection including speed enhancing and data flow reducing algorithms. The main examined methods were: frequency peaks, frequency bands, autocorrelation, frequency correlation methods and machine learning including deep machine learning. Deep machine learning of the neural network achieved the best results overall. Features from time and frequency domain were used for purposes of creating the classification model using machine learning. The possibility of developing the predictive maintenance system is also described, including research of this area in a modern industry. Subsequently, the achieved results and their evaluation are presented. The end of this thesis is dedicated to the description of the implementation of classification system into realtime form and connecting this system to the punching press computer using Arduino Uno microcontroller and basic signal control electronics. The proposed system has been successfully assembled, tested and put into on-site testing.
|
|
|
Application of Algorithms of Predictive Maintanence for RUL Estimation
Dvořák, Jan ; Brablc, Martin (referee) ; Dobossy, Barnabás (advisor)
The aim of this thesis is to acquaint the reader with the areas of predictive maintenance and its algorithms within its prognostic part. The remaining useful life of the system will be determined on the data sets and the performed experiment using prognostic models in accordance with the algorithms described in the research section. MATLAB and its other applications described in the work were used for data processing and modeling.
|
|
|
Proposal for Improvements of Predictive Maintenance Services and its Promotion
Stránský, Štěpán ; Cabejšek, Tomáš (referee) ; Kaňovská, Lucie (advisor)
Hlavním cílem této bakalářské práce je analyzovat divizi Power společnosti AXIMA a její konkurenty se zaměřením na chytré produkty a služby a na základě těchto analýz vytvořit návrhy na zlepšení a propagaci služeb prediktivní údržby AXIMA Power. První hlavní část je teoretická a obsahuje definice týkající se marketingu, používaných analýz a prediktivní údržby, následuje analytická část, kde je analyzována současná situace společnosti a jsou identifikovány klíčové faktory pro návrhy. Poslední část obsahuje návrhy aktivit zaměřených na zlepšení a propagaci služeb prediktivní údržby a chytrých produktů divize.
|
|
|
Data collection from 3D printer
Fiala, Jan ; Baštán, Ondřej (referee) ; Arm, Jakub (advisor)
This work is dedicated to design and implementation of a funcitonal model for data processing from 3D printer using sensors in IoT concept. Measured data will be processed and transfered to basic units with connection to the cloud server for any ongoing work. Part of this work is selection of suitable sensors and system members, creation of a functional model of data transfer and its implementation on a 3D printer.
|
|
| |
|
|
Train Identification System at Railway Switches And Crossings Using Advanced Machine Learning Methods
Krč, Rostislav ; Vorel,, Jan (referee) ; Plášek, Otto (referee) ; Podroužek, Jan (advisor)
This doctoral thesis elaborates possibilities of automatic train type identification in railway S&C using accelerometer data. Current state-of-the-art was considered, including requirements stated by research projects such as S-Code, In2Track or Turnout 4.0. Conducted experiments considered different architectures of artificial neural networks (ANN) and statistically evaluated multiple use case scenarios. The resulting accuracy reached up to 89.2% for convolutional neural network (CNN), which was selected as a suitable baseline architecture for further experiments. High generalization capability was observed as models trained on data from one location were able to classify locomotive types in the other location. Further experiments evaluated the effect of signal filtering and denoising. Evaluation of allocated memory and processing time for pre-trained models proved feasibility for in-situ application with regard to hardware restrictions. Due to a limited amount of available accelerometer data, distribution grid power demand data were utilized for further refinement of the proposed CNN architecture. Deep multi-layer architecture with regularization techniques such as dropout or batch normalization provides state-of-the-art performance for time series classification problems. Class activation mapping (CAM) allowed an explanation of decisions made by the neural network. Presented results proved that train type identification directly in the S&C is possible. The CNN was selected as optimal architecture for this task due to high classification accuracy, automatic filtration, and pattern recognition capabilities, allowing for the incorporation of the end-to-end learning strategy. Moreover, direct on-site application of pre-trained models is feasible with respect to limitations of in-situ hardware. This thesis contributes to understanding the train type identification problem and provides a solid theoretical background for future research.
|
guest ::
