• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 22
  • 1
  • Tagged with
  • 23
  • 14
  • 12
  • 11
  • 8
  • 6
  • 6
  • 5
  • 5
  • 5
  • 5
  • 4
  • 4
  • 4
  • 4
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
21

Machine Learning for Traffic Control of Unmanned Mining Machines : Using the Q-learning and SARSA algorithms / Maskininlärning för Trafikkontroll av Obemannade Gruvmaskiner : Med användning av algoritmerna Q-learning och SARSA

Gustafsson, Robin, Fröjdendahl, Lucas January 2019 (has links)
Manual configuration of rules for unmanned mining machine traffic control can be time-consuming and therefore expensive. This paper presents a Machine Learning approach for automatic configuration of rules for traffic control in mines with autonomous mining machines by using Q-learning and SARSA. The results show that automation might be able to cut the time taken to configure traffic rules from 1-2 weeks to a maximum of approximately 6 hours which would decrease the cost of deployment. Tests show that in the worst case the developed solution is able to run continuously for 24 hours 82% of the time compared to the 100% accuracy of the manual configuration. The conclusion is that machine learning can plausibly be used for the automatic configuration of traffic rules. Further work in increasing the accuracy to 100% is needed for it to replace manual configuration. It remains to be examined whether the conclusion retains pertinence in more complex environments with larger layouts and more machines. / Manuell konfigurering av trafikkontroll för obemannade gruvmaskiner kan vara en tidskrävande process. Om denna konfigurering skulle kunna automatiseras så skulle det gynnas tidsmässigt och ekonomiskt. Denna rapport presenterar en lösning med maskininlärning med Q-learning och SARSA som tillvägagångssätt. Resultaten visar på att konfigureringstiden möjligtvis kan tas ned från 1–2 veckor till i värsta fallet 6 timmar vilket skulle minska kostnaden för produktionssättning. Tester visade att den slutgiltiga lösningen kunde köra kontinuerligt i 24 timmar med minst 82% träffsäkerhet jämfört med 100% då den manuella konfigurationen används. Slutsatsen är att maskininlärning eventuellt kan användas för automatisk konfiguration av trafikkontroll. Vidare arbete krävs för att höja träffsäkerheten till 100% så att det kan användas istället för manuell konfiguration. Fler studier bör göras för att se om detta även är sant och applicerbart för mer komplexa scenarier med större gruvlayouts och fler maskiner.
22

Att ta beslut i ett självstyrande team : En kvalitativ studie för vardagligt beslutsfattande i självstyrande team / To make descisions in autonomous teams : A qualitative study to everyday decision-making in autonomous teams

Widstrand, Lisa, Kvarnevik, Albin January 2021 (has links)
Bakgrund: Organisationer förändras och övergår mer till teambaserad struktur samt utvecklar med självstyrande team. Självstyrande team har visat öka effektivitet och produktivitet i organisationerna. Den organisationsstruktur och -kultur som teamen besitter anses unik med strävan efter auktoritet i det vardagliga arbetet samt beslutsfattandet. Det är utmanande med självstyrande team som ska bestå av individer som ska förlita sig på varandra med ett gemensamt ansvarstagande och arbeta mot ett gemensamt mål. Vid första tanke är självstyrande team uppbyggda med grund att vara ledarlösa. Syfte: Syftet med studien är att undersöka och öka förståelsen för vardagligt beslutsfattande inom självstyrande team. Det som avses undersökas är förståelsen kring beslutsfattandets tillvägagångssätt samt teammedlemmars befogenhet för det vardagliga beslutsfattandet inom teamen. Metod: Metoden som har använts i denna studie är en kvalitativ forskningsmetod med abduktiv ansats. Det empiriska material som samlats in till studien bygger på sju semistrukturerade intervjuer samt en mängd sekundärdata från det valda tillverkningsföretaget. Det insamlade empiriska materialet har för avsikt med hjälp av den teoretiska referensramen, att analysera likheter och skillnader mellan teamen samt tidigare forskning. Slutsats: Studien bekräftar tidigare forskning om att självstyrande team ska styra över sitt eget ansvarstagande samt vardagliga beslutsfattande. Studien illustrerar dock att definitionen av självstyrande team är begränsad och behovet av stöd från ledarroller behövs. / Background: Organizations change and transition more to team-based structure and develop with autonomous teams. Autonomous teams have shown increased efficiency and productivity in organizations. The organizational structure and culture that the teams possess is considered unique with the pursuit of authority in everyday work and decision-making. It is challenging with autonomous teams that will consist of individuals who rely on each other with a shared responsibility and work towards a common goal. At first thought, autonomous teams are built on the basis of being leaderless. Purpose: The purpose of the study is to investigate and increase the understanding of everyday decision-making within autonomous teams. What is meant to be investigated is the understanding of the approach of decision-making as well as the power of team members for the day-to-day work of the teams. Method: The method used in this study is a qualitative research method with an abductive approach. The empirical material collected for the study is based on seven semi-structured interviews as well as a variety of secondary data from the selected manufacturing company. The collected empirical material intends to use the theoretical frame of reference to analyze similarities and differences between the teams and previous research. Conclusion: The study confirms previous research that autonomous teams should control their own responsibility and everyday decision-making. The study illustrates that the definition of autonomous teams is limited and the need for support from leadership roles is needed.
23

Stressprevention & Agil transformation : Prevention av organisatoriska rotorsaker till stress genom införandet av det Agila arbetssättet inom en högteknologisk multinationell svensk koncern

Fritz, Minanda January 2018 (has links)
Background: The Swedish Royal School of Technology (KTH) was hired to conduct a pilot study project on stress prevention, "Stress Prevention Project" in a Swedish high-tech global manufacturing company with headquarters in Sweden. The aim was to identify the root causes of stress among employees at the organizational level and to offer a way to prevent the root causes. The initiative to implement the project came from the HR department in the company. The occupational health department had not been able to lower the costs of sickness and rehabilitation. One of nine divisions was included in this evaluation study. The project was carried out during the years of 2012-2014, and three quantitative stress measurements were carried out using the modern working environment form “Modern Work Life” based of knowledge from KTH and designed by Metodicum. The present study has evaluated the root causes of the division's stress. In the division, it was stated that the risk areas that the division had to work with were: resources, demands, control, support but also leadership and reorganization with implementing the Agile methods (autonomous work) in the form of. The aim was to improve the psychosocial occupational health and to make the production work more efficient. Aim: The aim was to evaluate the effect of stress preventive measures in one of the nine divisions (that were included in the overall project) and the effect of implementing the Agile methods (autonomous work) in the organization. Limitations: The evaluation is restricted to one of the nine divisions. Method: The method is a quantitative and qualitative case study, with a narrative approach. The study includes a division with 200 employees of which data was collected from 18 of these employees in two focus groups interviews. Materials have also been collected from interviews with the division's HR director, section leader, head of unit and head of the organization's business health. The evaluation is based on qualitative data, which were obtained through 3 single interviews and 4 focus group interviews and participant observation. Quantitative data were obtained through three different measurements (between 2012-14). The quantitative data were compared and analyzed with the qualitative data in order to understand the results up to the final measurement 3 (2014). Results: The evaluation of the stress prevention – where the focus was to prevent risk areas including demands, develop resources, control, support and also leadership – showed that introducing and using the Agile working principles had had a significant positive effect on all the risk areas. Additionally, this change in the organization contributed to positive results regarding the efficiency of the production process; a reduction of working hours from 12 months to 2 weeks of action at the same result. The absence due to illness and rehabilitation has been decreasing from 4 % to 0,5-1% right after introducing the Agile methods in the division. However, the results also showed no improvement regarding some other working environment; as conflicts and bullying persisted. This may be due to how the reorganization of the groups was done. It should be clarified that the outcomes may be influenced by the extensive reorganization that took place in connection with the stress prevention project and the introduction of the agile approach. Conclusions - The stress prevention could not have been done efficiently due to other on-going reorganizations in the company and the staff has not been able to follow the recommendation for efficient stress-prevention due to lack of support from the headquarter. That created a crisis in the stress prevention-project group. The agile methods seem to have had a significant good result in all risk areas as resources, demands, control, support and also leadership and the absence has decreased from 4 to 0,5 %. Due to the agile methods have the productions process been shorter from 12 months to 2 weeks.

Page generated in 0.3805 seconds