Idag finns det många böcker och utrustningar för att bidra till en säker färd i vildmark, men marknaden inom området har en stor potential för utveckling. Projektet har tagit fram två prototyper för att mäta vattenintaget vid en färd i vildmark med varningssignaler som visar när vattentillståndet är kritiskt och för att påminna användare att dricka vatten. Prototyperna har jämfört och slutsatser har dragit för vilken prototyp som är mest optimal för ändamålet. / Today there are many books and equipment that contribute to a safe journey in the wildness. But the market still has a great potential for development. In this project two prototypes has been developed to control the users hydration level when hiking in wildness. The measurement system shows a warning signal when the water level is too low. The two prototypes have been compared and a conclusion has been drawn for which prototype is themost optimal for the projects purposes.

Det finns många sensormetoder för vattennivåmätning ute på marknaden idag. Målet för forskningsstudien är att presentera och jämföra några av de mätningsmetoder som finns på marknaden för nivåmätning. I studien jämförs modellerna för trycksensorer, flytsensorer, ultraljudssensor och elektromagnetisk sensor för att sedan se vilken sensor som passar bäst för just mätningar av vattennivåer. Genom, datainsamlingen från sök motorerna Google scholar och Mittuniversitetets egen databas Primo har fakta samlats. Informationen har sedan bearbetas och jämförts mot behoven från Vattenfall som ska göra tre sensorbyten på vattenkraftverket i Stugun. Resultatet av studien visade slutsatsen att utifrån kravspecifikationerna Vattenfall gav så var en trycksensor det bästa alternativet för Stugun. Studien gjorde så att Vattenfall köpte in tre stycken Waterpilot FMX21, 22 mm som sedan sattes på plats och kalibrerades. / There are many sensor methods for water level measurement on the market today. The aim of the research study is to present and compare some of the measurement methods available on the market for level measurement. In the study, the models for pressure sensors, flow sensors, ultrasonic sensors and electromagnetic sensors are compared to see which sensor is most suitable for precise measurements of water levels. Through the data collection from the search engines Google scholar and Mid University of Sweden own database Primo, facts have been gathered. The information has since been processed and compared to the needs of Vattenfall, which will do three sensor changes at the Stugun hydropower plant. The result of the study showed that according to the requirement specifications of Vattenfall, a pressure sensor was the best alternative for Stugun. The study resulted in Vattenfall purchasing three Waterpilot FMX21, 22 mm, which were then put in place and calibrated.

Agriculture is becoming more dependent on computerized solutions to make thefarmer’s job easier. The big step that many companies are working towards is fullyautonomous vehicles that work the fields. To that end, the equipment fitted to saidvehicles must also adapt and become autonomous. Making this equipment autonomoustakes many incremental steps, one of which is developing an accurate and reliable tanklevel measurement system. In this thesis, a system for tank level measurement in a seedplanting machine is evaluated. Traditional systems use load cells to measure the weightof the tank however, these types of systems are expensive to build and cumbersome torepair. They also add a lot of weight to the equipment which increases the fuel consump-tion of the tractor. Thus, this thesis investigates the use of radar sensors together witha number of Machine Learning algorithms. Fourteen radar sensors are fitted to a tankat different positions, data is collected, and a preprocessing method is developed. Then,the data is used to test the following Machine Learning algorithms: Bagged RegressionTrees (BG), Random Forest Regression (RF), Boosted Regression Trees (BRT), LinearRegression (LR), Linear Support Vector Machine (L-SVM), Multi-Layer Perceptron Re-gressor (MLPR). The model with the best 5-fold crossvalidation scores was Random For-est, closely followed by Boosted Regression Trees. A robustness test, using 5 previouslyunseen scenarios, revealed that the Boosted Regression Trees model was the most robust.The radar position analysis showed that 6 sensors together with the MLPR model gavethe best RMSE scores.In conclusion, the models performed well on this type of system which shows thatthey might be a competitive alternative to load cell based systems.