TSI logo 25 years
LV EN
Home > About Us > Structure and Government > Abstracts

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

Automation of the parcel distribution process in a postal department

This thesis is devoted to automating the process of parcel distribution in the post office to increase the speed and accuracy of processing in the face of the growing demand of e-commerce. The limitations of the existing manual sorting system were analyzed and an automated solution was developed. The work defines the technical parameters and functions of the system, including the operation of conveyors, accurate data collection and parcel sorting. Structural and functional diagrams are developed, and the selection of components such as scanning devices, sorting machines, conveyors, sensors and PLCs is described. The algorithm and control program for the system were created and tested using the STEP 7 development environment and FactoryIo. The proposed automated system is aimed at significantly increasing productivity and reducing errors in the parcel processing process.

Author: Aleksandrs Panteļejevs

Supervisor: Vasilijs Gredasovs

Degree: Bachelor

Year: 2024

Work Language: English

Comparative analysis of RPL protocol objective functions impact on energy consumption in low-power and lossy networks

This bachelor thesis explores the impact of different RPL protocol objective functions on energy consumption in low-power and lossy networks. Given the critical role of low-power and lossy networks in applications like environmental monitoring, industrial automation, and smart cities, optimising energy consumption is paramount. Using the Contiki-NG operating system and the Cooja network simulator, this study conducts a comparative analysis of two primary objective functions: Objective Function Zero and Minimum Rank with Hysteresis Objective Function. Simulations are performed under 18 network scenarios including different node densities (10, 30, 50), node positioning, and receive ratios. The findings indicate that Objective Function Zero generally consumes less energy, particularly in high-density networks and environments with high packet delivery ratios. Conversely, Minimum Rank with Hysteresis Objective Function may be more suitable for dynamic and unpredictable environments despite its higher energy consumption. This research offers practical recommendations for selecting objective functions to optimise the energy consumption of constrained networks, contributing to the development of more sustainable IoT solutions.

Author: Deniss Bogdans

Supervisor: Jeļena Baranova

Degree: Bachelor

Year: 2024

Work Language: English

Research on effective finding of network anomalies in Intrusion Detection Systems using ML/DL methods

In this paper, the process of testing datasets and ML/DL methods using the Weka platform in order to obtain results of their effectiveness and how high the accuracy of detecting network anomalies they provide is described. During the experiment, many ML/DL algorithms and the most common datasets (KDD99, NSL-KDD, UNSW-NB15) were analyzed, as a result of which it was revealed that the best result of detection accuracy and time required on the experiment was produced by the NSL-KDD dataset.

Author: Dmitrijs Bulaks

Supervisor: Jeļena Baranova

Degree: Bachelor

Year: 2024

Work Language: English

Corporate Network Segmentation to Security Level Improving

The aim of the bachelor thesis is Corporate Network Segmentation to Security Level Improving. During the audit of the company's network, several problems were identified, such as a single network, weak nodes, no backup channel, a separate strand with Lithuanian servers, HQ branch without a backup channel. The most popular network security threats and attacks were reviewed, DiD strategies and measures were introduced, an audit of the existing computer network was performed, and the new network topology was drawn. Based on the Cisco PPDIOO model, a plan for gradual restructuring in a new network has been drawn up. A central device was installed in the DC of Latvia, an IPsec tunnel was agreed with the DC of Lithuania, tests were carried out. All branches were provided with backup channels, which made it possible to test a new network first through the backup channel and only when all the tests were performed and were positive, the main channel could easily be connected as well. The backup channel routers and branch routers are configured according to a single template to allow easy interchangeability. Configured access to branch switches and backup routers from both channels: primary channel and backup channel. The network has been tested and is working.

Author: Igors Manžurcevs

Supervisor: Elena Revzina

Degree: Bachelor

Year: 2024

Work Language: English

Vibration Analysis-Based Fault Diagnosis of Tool Conditions on Electric Motor-Powered Machine Tools Using Convolutional Neural Networks

This thesis explores and evaluates techniques for utilizing vibration analysis and Convolutional Neural Networks (CNNs) to assess the condition of drill bits installed on electric motor-driven drills. By strategically positioning an Inertial Measurement Unit (IMU) sensor to capture acceleration data, a wide range of vibration signals can be gathered in different operational scenarios. The CNN models undergo training and validation utilizing this data to precisely detect various fault conditions and operational states of the drill bits, showcasing the possibility of implementing scalable and reliable fault detection systems in industrial environments. The research attains a Technology Readiness Level (TRL) of 3, as demonstrated by trials that effectively categorize machine conditions using CNNs, hence confirming the critical functions of the proposed technology. The aim of this study is to assess the efficacy of vibration analysis in classifying the operational state of a drilling machine as either good, moderate, or bad.Vibration analysis is a method used to analyze the oscillation patterns of a machine in order to identify problems such as misalignment, imbalance, and wear.

Author: Marawan Mohamed Ahmed Elsayed Youssef

Supervisor: Emmanuel Alejandro Merchan Cruz

Degree: Master

Year: 2024

Work Language: English

Table View
Text View