Thesis (M.Eng.)--University of Wollongong, 2005. / Typescript. Includes bibliographical references: leaf 84-89.

Šio darbo tikslas suprojektuoti ir sukurti nesudėtingą garsinio signalo apdorojimo realiu laiku įtaisą, populiaraus „Arduino“ mikrovaldiklio pagrindu, kuriuo būtų lengva naudotis ir būtų galimybė pagrindines funkcijas valdyti naudojantis TC/IP protokolu. „Arduino“ mikrovaldiklis pasirinktas dėl jo populiarumo, prieinamos kainos ir dėl gausios informacijos, apie jo panaudojimo galimybes. Be abejo yra daug ir kitų platformų skirtų įvairių prietaisų kūrimui su pakankamai išsamia informacija, bet „Arduino“ platformai yra sukurta nemokama atviro kodo programinė įranga, „Arduino“ kontrolerio programavimui tiesiogiai iš personalinio kompiuterio, nenaudojant papildomų priemonių, dirbanti su Windows ir Unix operacinėmis sistemomis. / Most modern desktop computers are equipped with audio hardware. This hardware allows audio to be recorded as digital information for storage and later playback. This digital information can be manipulated to change how the audio sounds when played back. But if we don’t have a computer, or just need to get some sound effects quickly without recording audio? Maybe You are a student who are learning sound processing hardware and need some examples of audio synthesis? Do you like an “Arduino” and want to see what it can? This device is for You! This small device based on “Arduino” controller makes audio processing in real time, producing some audio effects and also it can play some synthetic sound. In this device is integrated LCD screen, where you can see some information about what the device is doing, when you have pressed one of some buttons on it. Also it is possible to manage the device over the internet. You need just plug in an Ethernet cable, open an internet browser on the computer in local network and add an IP address of this device. You will get small web page where you will found few buttons. By clicking with mouse on these buttons you can listen to a synthetic sound, which system can produce. In this work You will be introduced to the sound signal processing. You will also find graphs and flowchart detailing the sequence of event between the user and system, the exchange of data inside and the static structure of the system in the architectural specification. In... [to full text]

Induction motor is the most popular machine in the industry. It is used extensively in mechanical plants, and it is un- avoidable to have the motor¡¦s electrical and mechanical faults due to continuously operating throughout the year. Faults of motors do not only cause the production line to shut down but also imperil the personnel security. A suitable motor maintenance schedule will be a needed to decrease the machine down time. However, major investment might take up to 90% for equipment, and it would be helpful to have a practicable low-cost supervisory scheme on maintenance. If the faults of machine can be detected correctly and effectively, the maintenance efficiency and dependability could be increased greatly. In the past, researches on fault recognition for Induction motors only concentrated on Spectrum analysis with amplitudes based on a constant load. However, the frequency and amplitude of the spectrum analyzed under different fault conditions are also affected significantly by load variations. Using spectrum amplitudes to recognize motor faults is not sufficient in a practical system. Various types of faults and load conditions will influence the spectrum structure. In order to recognize faults under various load conditions, we must consider band shift and amplitude variation as two major factors. In this paper, we use the methods of frequency axis adjustment, load interval and feature exaction to solve the band shift and amplitude variation problems respectively. After the above-mentioned procedures, efficient features are obtained. We use the Back Propagation Neural Network (BPNN) and General Regression Neural Network (GRNN) to train and recognize fault conditions.

Thesis (M. Sc.)--University of Hong Kong, 1998. / Includes bibliographical references (leaf 32-34).

Thesis (M.S.)--Naval Postgraduate School (Monterey, Calif.), 1991. / Cover title. "September, 1991." Includes bibliographical references (leaves 123-125).

This paper describes the methods used mainly in the filtration of audio signals -- noise reduction. It realizes segmentation with variable lenght of segment, constant overlap add and segmentation with variable lenght of segment and overlap add. These methods are then compared with comon methods of segmentation in dependance of the lenght of segment and used window function by the thresholding method. For this purpose it uses the database of audio records. In the first part it desrcibes the technique of audio signal processing with comon method of segmentation. According to this method it continues in design of signal processing by variable segmentation method, in which it is needed to modify the shape of window function, which influences and attributes are explained in next chapter. In practical part it describes the implemented methods in MATLAB programming language with each steps of testing. It continues with chart of enclosed files and the evaluation of the results of hearing tests.

In this study, a mathematical model is developed for investigating the discrete sound propagation in viscoelastic medium to identify its viscoelastic properties. The outcome of the model suggests that pulse repetition frequency is a very important parameter for the determination of relaxation time. Adjusting the order of magnitude of the pulse repetition frequency, the corresponding relaxation time which has similar magnitude with pulse repetition frequency is filtered while the others in the spectrum are discarded. Discrete relaxation spectrum can be obtained by changing the magnitude of the pulse repetition frequency. Therefore, the model enables to characterize the relaxation times by ultrasonic measurements.

In industry, it is crucial to be able to detect damage or abnormal behavior in machines. A machine's downtime can be minimized by detecting and repairing faulty components of the machine as early as possible. It is, however, economically inefficient and labor-intensive to detect machine fault sounds manual. In comparison with manual machine failure detection, automatic failure detection systems can reduce operating and personnel costs.  Although prior research has identified many methods to detect failures in drill machines using vibration or sound signals, this field still remains many challenges. Most previous research using machine learning techniques has been based on features that are extracted manually from the raw sound signals and classified using conventional classifiers (SVM, Gaussian mixture model, etc.). However, manual extraction and selection of features may be tedious for researchers, and their choices may be biased because it is difficult to identify which features are good and contain an essential description of sounds for classification. Recent studies have used LSTM, end-to-end 1D CNN, and 2D CNN as classifiers for classification, but these have limited accuracy for machine failure detection. Besides, machine failure occurs very rarely in the data. Moreover, the sounds in the real-world dataset have complex waveforms and usually are a combination of noise and sound presented at the same time. Given that drill failure detection is essential to apply in the industry to detect failures in machines, I felt compelled to propose a system that can detect anomalies in the drill machine effectively, especially for a small dataset. This thesis proposed modern artificial intelligence methods for the detection of drill failures using drill sounds provided by Valmet AB. Instead of using raw sound signals, the image representations of sound signals (Mel spectrograms and log-Mel spectrograms) were used as the input of my proposed models. For feature extraction, I proposed using deep learning 2-D convolutional neural networks (2D-CNN) to extract features from image representations of sound signals. To classify three classes in the dataset from Valmet AB (anomalous sounds, normal sounds, and irrelevant sounds), I proposed either using conventional machine learning classifiers (KNN, SVM, and linear discriminant) or a recurrent neural network (long short-term memory). For using conventional machine learning methods as classifiers, pre-trained VGG19 was used to extract features and neighborhood component analysis (NCA) as the feature selection. For using long short-term memory (LSTM), a small 2D-CNN was proposed to extract features and used an attention layer after LSTM to focus on the anomaly of the sound when the drill changes from normal to the broken state. Thus, my findings will allow readers to detect anomalies in drill machines better and develop a more cost-effective system that can be conducted well on a small dataset. There is always background noise and acoustic noise in sounds, which affect the accuracy of the classification system. My hypothesis was that noise suppression methods would improve the sound classification application's accuracy. The result of my research is a sound separation method using short-time Fourier transform (STFT) frames with overlapped content. Unlike traditional STFT conversion, in which every sound is converted into one image, a different approach is taken. In contrast, splitting the signal into many STFT frames can improve the accuracy of model prediction by increasing the variability of the data. Images of these frames separated into clean and noisy ones are saved as images, and subsequently fed into a pre-trained CNN for classification. This enables the classifier to become robust to noise. The FSDNoisy18k dataset is chosen in order to demonstrate the efficiency of the proposed method. In experiments using the proposed approach, 94.14 percent of 21 classes were classified successfully, including 20 classes of sound events and a noisy class. / <p>Vid tidpunkten för disputationen var följande delarbeten opublicerade: delarbete 2 och 3 inskickat.</p><p>At the time of the doctoral defence the following papers were unpublished: paper 2 and 3 submitted.</p> / AISound – Akustisk sensoruppsättning för AI-övervakningssystem / MiLo — miljön i kontrolloopen

This paper presents parameters of evaluation of acoustic quality of the space. It is divided into parts presenting physical principle of the origin and movement of the acoustic signal, principles of its processing with current technology and properties of the acoustic field. This is followed by an analysis of the musical part and notes on psychoacoustics. The document contains a description of relevant parameters of acoustic spaces and way in which we can reach desired results, including material analysis. The paper mainly focuses on description of relevant parameters of three acoustic spaces which were measured. The last part of the work is a program for elementary acoustical measurement, which can be provided by means of commonly accessible equipment such as a notebook or a personal computer.