When ice is accumulated on a wind turbine's rotor blade its aerodynamics are altered, leading to reduced efficiency and sometimes altered pressure oscillations around the blade. These pressure oscillations can be detected as sound. With sound level measurements over a long time, combined with known ice conditions in the same period, the measured sound data can be used to classify the ice conditions. This master's thesis aims to investigate the possibilities of using sound level measurements at 36 frequency bands in the range 6.3–20 000 Hz along with machine learning and wind speed to detect icing on wind turbine blades. Four k-NN models have been trained and evaluated using two different data configurations that each treat two different means of normalization: one uses the raw sound level data in dBA which has been standardized using z-score. The other uses the wind power density Iwind = 0.5ρU3 instead of the reference sound intensity I0 = 10-12 W/m2 in the decibel formula L = 10log10(I/I0) to reduce the influence of wind speed on the data. The sound/wind speed hybrid data was also z-score standardized. Available data was from February 21st to March 3rd in 2023 and March 1st to April 3rd in 2024. In the summer of 2023, the leading edges of the rotor blades on the investigated wind turbine were renovated which might have altered the sound. Therefore, what is denoted as Data configuration A used 2024 data as training data while 2023 data was used solely for testing. Data configuration B on the other hand used data from March 1st to March 17th 2024 for training and data from April 1st to April 3rd 2024 for testing as the rotor blades were identical between those data sets. Wind conditions were also more similar between training and testing data for Data configuration B. The models were optimized using grid search, varying k, distance metrics and feature combinations of the 36 frequency bands, while maximizing the balanced accuracy, BA, of the model using 5-fold cross-validation. For Data configuration A, this resulted in a balanced accuracy in the testing stage at BAtesting = 0.535 using the dBA sound level data, and BAtesting = 0.601 using the data normalized with wind power density. For Data configuration B, balanced accuracy was BAtesting = 0.845 using the dBA sound level data, and BAtesting = 0.773 using the data normalized with wind power density. The main conclusion is that icing can be detected using sound level measurements, wind speed and machine learning although the models in this project generalize poorly partly due to limited data and partly due to how the models were constructed. The models perform better with wind speeds similar to the training data. / När is ackumuleras på vindturbinblad ändras aerodynamiken vilket leder till lägre verkningsgrad och ibland förändrade tryckoscillationer kring bladet. Dessa tryckoscillationer kan detekteras i form av ljud. Med hjälp av ljudmätningar över en längre tid, kombinerat med kända isförhållanden under tidsperioden, kan ljuddatan användas för att klassificera isförhållandena. Målet med detta examensarbete är att undersöka möjligheterna att använda ljudnivåmätningar vid 36 frekvensspann mellan 6,3–20 000 Hz tillsammans med maskininlärning och vindhastighet för att detektera isbildning på vindkraftverk. Fyra modeller baserade på algoritmen k-NN har tränats och utvärderats med två olika datakonfigurationer som vardera behandlar två olika metoder för normalisering: en använder obehandlad ljudnivådata i enheten dBA som har standardiserats med z-poäng. Den andra använder vindenergidensiteten Iwind = 0.5ρU3 istället för referensintensiteten I0 = 10-12 W/m2 i formeln för decibel L = 10log10(I/I0) för att begränsa vindhastighetens inverkan på datan. Ljud-/vindhybriddatan standardiserades också med z-poäng. Den tillgängliga datan var mellan 21 februari och 3 mars 2023 samt 1 mars till 3 april 2024. Sommaren 2023 renoverades bladen på det undersökta vindkraftverket vilket kan ha påverkat ljudet. Därför användes data från 2024 som träningsdata och data från 2023 som testdata i vad som benämns som Data configuration A. Data configuration B använde istället data från 1-17 mars 2024 för träning och data från 1-3 april 2024 för testning eftersom rotorbladen var identiska mellan de datamängderna. Vindförhållandena var också mer lika inom Data configuration B. Modellerna optimerades med grid search genom att variera k, avståndsmått, och vilken kombination av de 36 frekvensspannen som ingår i modellen. Balanserad träffsäkerhet, BA, är resultatet som maximerades genom 5-delad korsvalidering. För Data configuration A resulterade detta under teststadiet i BAtesting = 0,535 med omodifierad ljuddata och BAtesting = 0,601 då vindenergidensiteten användes som ljudets referensnivå. För Data configuration B var den balanserade träffsäkerheten BAtesting = 0,845 med omodifierad ljuddata och BAtesting = 0,773 då vindenergidensiteten användes som ljudets referensnivå. Den främsta slutsatsen är att isbildning kan detekteras med ljudnivåmätningar, vindhastighet och maskininlärning men modellerna som har tagits fram i detta projekt presterar relativt dåligt, delvis på grund av en begränsad datamängd och delvis på grund av hur modellerna har konstruerats. Modellerna presterade bättre för testdata med liknande vindförhållanden.

La zona en estudio, ubicada entre los kilómetros 31 y 35 de la carretera Panamericana Norte, posee un nivel de presión sonora promedio de 76.48dB y 74.76dB en el horario diurno y nocturno respectivamente, y tomando como base Los Estándares de Calidad de Ruido Ambiental (ECA) se puede determinar que la zona en estudio se produce contaminación acústica. Por ello, las personas que frecuentan y/o circulan por esta zona se encuentran propensas a contraer distintas enfermedades y molestias producto de la contaminación sonora, entre ellas: Estrés, pérdida de audición con el paso del tiempo, problemas cardiológicos, entre otros. Ante lo mencionado, la presente tesis busca controlar el ruido generado por el parque automotor mediante la instalación de Barreras Acústicas en la sección vial de la Panamericana Norte, utilizando como materiales principales dos tipos de concreto, el concreto convencional y el concreto con agregados ligeros de aserrín y viruta. Para ello, el concreto con agregados ligeros de aserrín y viruta, material absorbente del sistema de Barrera Acústica, se lleva al laboratorio acústico para ensayar mediante el método del Tubo de impedancia, para obtener el coeficiente de nivel de presión sonora. Siendo este valor promedio de absorción sonora máxima de las muestras (α) 0.23. En conclusión, el sistema de barrera acústica diseñado alcanza a absorber hasta 23% del nivel de presión sonora percibido, y con ello la zona en estudio se encuentra dentro de los Estándares de Calidad de Ruido Ambiental. / The area under study, located between kilometer 31 and kilometer 35 of the Northern Pan-American Highway, has an average sound pressure of 76.48dB during daytime and 74.76dB during nighttime. Taking the Environmental Noise Quality Standards (ECA, in Spanish) into consideration, it can be determined that the noise pollution occurs in the area under study. Therefore, the people who frequent or pass by this area are prone to contract various diseases or malaise as a result, such as stress, gradual hearing loss, heart issues, among others. Given the situation, this thesis aims at controlling the noise produced by motorized vehicles by installing sound barriers on said road section of the Northern Pan-American Highway, using two types of concrete as main materials: conventional concrete and concrete with light sawdust and woodchip aggregates. The concrete with light sawdust and swarf aggregates, absorbent material of the sound barrier system, is taken to the sound laboratory to perform tests through the impedance tube method to obtain the sound pressure level. This is the average value of the maximum absorption level of the samples (α) 0.23. In conclusion, the designed sound barrier system manages to absorb up to 23% of the perceived sound pressure level. With that, the area under study falls within the Environmental Noise Quality Standards. / Tesis

Sound levels in live sound reinforcement have long been a topic for debate in live concerts, but the subject is also important elsewhere. Swedish Christian free churches have also struggled for many years to optimize how sound reinforcement can serve the community. There are many different factors affecting the sound level preferences in live sound reinforcement environments. Among them are perception of loudness, musical preferences, hearing impairments and tolerances. This bachelor thesis investigated if musical preference affected the perceived loudness and/or the preferred listening level through a set of listening tests and qualitative surveys. It was investigated in one Swedish free church congregation, from which 16 subjects participated. The listening test was conducted with three parts: loudness matching stimuli to a pink noise, setting the preferred listening level of the stimuli and rating the preference of the stimuli. Subsequently, a survey after a service was conducted to investigate different factors affecting the experience. No connection between music preference and loudness perception or preferred level wasfound. However, the study did produce multiple findings that reveal factors affecting the sound level preferences in the chosen congregation, such as hearing impairments, expectations on the role of sound in worship services, and the balance of instruments. These findings revealed differences in opinion regarding the mix philosophy used in services, and the impact of these approaches on members of the congregation. Altogether, the findings point to recommendations and considerations for live sound engineers working in worship environments.

This doctoral thesis focuses on noise generated during construction. It defines the legislative and physical aspects of this topic. It determines heavy machinery as noise source and categorizes them by their usage in construction technologies. It collects source data of the machinery noises which can be further used in prognostic models. It analyses the level of construction noise which can impact the nearby residential areas and offers methodology for modelling and designing the possible arrangements for the noise reduction. It defines partial effects of the construction site which are significant for the noise spreading. It establishes their role in the value of acoustic pressure level of the noise affecting the façade of the considered building. With the data collection and with case study verification it offers a prepared work tool which can be easily used to predict noise levels on construction sites and can be applied in the early constructions preparations. The structure of this thesis is planned for possible usage as university textbook or study support.