Sound Sensor Research Articles

Automatic Noise Monitor and Control in Library

Abstract: This paper introduces imperative to sustain a study-friendly atmosphere in libraries, as noise levels can greatly influence patron satisfaction. In order to reduce noise levels in libraries, this project suggests designing and implementing an autonomous noise monitoring and control system. The device constantly measures ambient noise levels by comparing them to predetermined thresholds using sound sensors and an Arduino. The technology reminds users to keep the environment quiet by sounding alerts and displaying visual cautions when acceptable limits are exceeded. To further reinforce silent norms, automatic audio announcements can be incorporated.

IoT-Based Connected Environmental Monitoring System Using NodeMCU

The Connected Environmental Monitoring System leverages the NodeMCU ESP8266 microcontroller in conjunction with various sensors, including the MQ-135, DHT22, BMP280, and a sound sensor, to enable real-time monitoring of critical environmental parameters. This project aims to provide comprehensive insights into air quality, temperature, humidity, atmospheric pressure, and noise levels, fostering awareness and informed decision-making regarding environmental conditions. Data collected by the sensors is transmitted wirelessly to the ThingSpeak cloud platform, where it is stored and visualized through user-friendly dashboards. The system also incorporates alert mechanisms to notify users when specific parameters exceed predefined thresholds, facilitating timely interventions. The modular architecture of the system allows for scalability and flexibility, making it adaptable for various applications, including urban management and smart city initiatives. Overall, this project demonstrates the efficacy of IoT solutions in addressing environmental monitoring challenges, contributing to the development of sustainable practices and enhanced community well-being.

Sub-millisecond keyhole pore detection in laser powder bed fusion using sound and light sensors and machine learning

Abstract Laser powder bed fusion is a mainstream additive manufacturing technology widely used to manufacture complex parts in prominent sectors, including aerospace, biomedical, and automotive industries. However, during the printing process, the presence of an unstable vapor depression can lead to a type of defect called keyhole porosity, which is detrimental to the part quality. In this study, we developed an effective approach to locally detect the generation of keyhole pores during the printing process by leveraging machine learning and a suite of optical and acoustic sensors. Simultaneous synchrotron x-ray imaging allows the direct visualization of pore generation events inside the sample, offering high-fidelity ground truth. A neural network model adopting SqueezeNet architecture using single-sensor data was developed to evaluate the fidelity of each sensor for capturing keyhole pore generation events. Our comparative study shows that the near infrared images gave the highest prediction accuracy, followed by 100kHz and 20kHz microphones, and the photodiode sensitive to processing laser wavelength had the lowest accuracy. Using a single sensor, over 90% prediction accuracy can be achieved with a temporal resolution as short as 0.1 ms. A data fusion scheme was also developed with features extracted using SqueezeNet neural network architecture and classification using different machine learning algorithms. Our work demonstrates the correlation between the characteristic optical and acoustic emissions and the keyhole oscillation behavior, and thereby provides strong physics support for the machine learning approach.

Application of digital transformation tools in dairy cattle farming and their role in improving population health and animal productivity

The aim of the study is to explore the ways of implementing digital technologies and modern technical solutions to ensure the population health of animals in the context of contemporary dairy farming. The paper discusses modern digital technical tools and automated processes in dairy farming facilitated by these tools. In the course of the study, the main tasks for successful digital transformation and ensuring the population health of animals in dairy farming were identified: searching for biomarkers of pathological and physiological states of animals, developing methods for determining found biomarkers, developing technical solutions for parameter registration and their implementation into production. At the moment, automatic systems for diagnosing the state of the animal’s body have been implemented using sound sensors, devices for determining the activity of the animal and the position of the body in space. Sensors for determining the electrical conductivity of milk make it possible to determine mastitis at the initial stage of the pathological process. Sensors for determining the concentration of hormones in milk make it possible to determine the period of the sexual cycle. ICS cameras allow you to determine areas of inflammation on the animal’s body. A modern 3-D camera system, combined with software, allows automatic measurement of animal body parameters on a daily basis. Thus, the implemented automated systems make it possible to reduce the time of human contact with an animal, which has a positive effect on the health of the animal. On the other hand, constant monitoring of important indicators of animal health allows timely detection of the onset of the disease. All of the above helps ensure population health on dairy farms.

Sound Sensing: Generative and Discriminant Model-Based Approaches to Bolt Loosening Detection.

The detection of bolt looseness is crucial to ensure the integrity and safety of bolted connection structures. Percussion-based bolt looseness detection provides a simple and cost-effective approach. However, this method has some inherent shortcomings that limit its application. For example, it highly depends on the inspector's hearing and experience and is more easily affected by ambient noise. In this article, a whole set of signal processing procedures are proposed and a new kind of damage index vector is constructed to strengthen the reliability and robustness of this method. Firstly, a series of audio signal preprocessing algorithms including denoising, segmenting, and smooth filtering are performed in the raw audio signal. Then, the cumulative energy entropy (CEE) and mel frequency cepstrum coefficients (MFCCs) are utilized to extract damage index vectors, which are used as input vectors for generative and discriminative classifier models (Gaussian discriminant analysis and support vector machine), respectively. Finally, multiple repeated experiments are conducted to verify the effectiveness of the proposed method and its ability to detect the bolt looseness in terms of audio signal. The testing accuracy of the trained model approaches 90% and 96.7% under different combinations of torque levels, respectively.

A view on distributed sound level sensors from the perspective of legal metrology

Paper-based calibration certificates are gradually being replaced by equivalent digital calibration certificates (DCCs). The DCC is human-readable as well as machine-readable which simplifies the administration process significantly. During calibration procedure a measurement instrument is tested on-site in a testing laboratory. However, nowadays sound level sensors are increasingly deployed as distributed systems, where they transmit measurement data from one location (e.g. a workplace in a factory) to a measurement laboratory over available networks. This data transmission process has until now not been considered during calibration procedure or type approval tests. Therefore, requirements for the data transmission process according to the regulations of the European Cooperation in Legal Metrology (WELMEC Guide) must be considered. In this project two digital sound level sensors were selected and tested when deployed as distributed systems. The data collected were used to compare the two systems in accordance with the regulations of the WELMEC guide. In this work the first example of an acoustical DCC is presented and discussed. Further, a list of requirements is proposed that should be considered in the future when developing sound level sensors intended to be used as distributed systems.

Acoustic characterization of porous windscreens for sound pressure and particle velocity sensors

Acoustic measurements of ground vehicles, wind turbines or aircrafts are often performed outdoors in presence of wind. Air movement around an acoustic sensor may significantly disturb the measured signals due to flow-induced vibrations and turbulence. This is specially relevant for pressure-gradient and particle-velocity based acoustic transducers which are more sensitive to these perturbations. To attenuate this effect and improve measurement quality, the sensors are typically covered with windscreens made of porous materials. However, designing an appropriate windscreen poses a challenging task, demanding a deep understanding of sound transmission characteristics. This study works towards quantifying acoustic properties of rigid-frame porous materials through in-situ measurements and fitting a parametric fluid-equivalent model to find optimal model parameters. The parameters are subsequently investigated by comparing windscreen insertion loss through finite-element numerical simulations and measurements on a sound intensity PU probe.

Characterizing urban acoustic environments by clustering sensor node measurements

Equivalent sound pressure levels have been widely used to assess the impact of the sonic environment on persons. At the same time, it has been demonstrated that sound sensor networks allow to extract a wealth of information about the living environment. Nevertheless it has not been clearly demonstrated how to summarize this information. To this end, we used advanced non-linear clustering methods to group 15-minute sound environments based on a wide range of classical acoustic indicators such as peak levels, statistical levels, spectral center of gravity. Machine learning methods identifying the sound sources that are present based on 1/3 octave band levels measured at 125 msec interval, are then used to better understand why these clusters emerge. The methodology is applied to 150 bedroom window measurements gathered in the Equal-Life project. Preliminary results show that groups of pre-school children with specific cognitive development and mental health are related to different diurnal patterns of sound environment clusters. These results can be interpreted in the larger context of living environments extracted from environmental sound sensing networks.

End-to-end training of acoustic scene classification using distributed sound-to-light conversion devices: verification through simulation experiments

We propose a framework for classifying acoustic scenes utilizing distributed sound sensor devices capable of sound-to-light conversion, which we term as Blinkies. These Blinkies can convert acoustic signals into varying intensities of light via an inbuilt light-emitting diode. By using Blinkies, we can aggregate the spatial acoustic information across a wide region by recording the fluctuating light intensities of numerous Blinkies distributed throughout the region. Nonetheless, the signal communicated is subject to the bandwidth limitation imposed by the frame rate of the video camera, typically capped at 30 frames per second. Our objective is to refine the process of transforming sound into light for the purpose of acoustic scene classification within these bandwidth confines. While traversing through the air, a light signal is affected by inherent physical limitations such as the attenuation of light and interference from noise. To account for these factors, we have integrated these physical constraints into differentiable physical layers. This approach enables us to jointly train a pair of deep neural networks for the conversion of sound to light and for the classification of acoustic scenes. Our simulation studies, which employed the SINS database for acoustic scene classification, demonstrated that our proposed framework outperforms the previous one that utilized Blinkies. These findings emphasize the effectiveness of Blinkies in the field of acoustic scene classification.

Development of an IoT-enabled smart baby cradle for enhanced infant monitoring and parental control

raditional infant monitoring systems are evolving into intelligent solutions, offering real-time notifications and automation to cater to the demands of multitasking parents. However, most IoT solutions in parental care focus solely on monitoring, lacking automatic smartphone control. In response to this gap, we developed an IoT-based system for automatic cradle monitoring. This system not only enables smartphone-based monitoring but also allows parents to control the cradle's swing speed and receive notifications through a mobile application. Our solution integrates PIR and sound sensors, an ESP8266 microcontroller, and a Wi-Fi module to create a robust monitoring system that tracks a baby's movements and sounds, sending instant notifications to the smartphone. The user can activate the system and adjust the cradle's motion using a slider based on sensor data. This IoT-enabled smart baby cradle enhances convenience and reduces parental stress, ensuring infant well-being and safety. A survey conducted among Universiti Teknologi MARA instructors revealed that 70% preferred automatic swing cradles over traditional ones, and 80% expressed the need for IoT integration in infant cradles, highlighting the growing demand for such advanced solutions.

Characterization of the cough monitoring device for TB patients based on the MAX9814 sound sensor

Characterization of the cough monitoring device for TB patients based on the MAX9814 sound sensor

Exploring the application of piezoelectric ceramics in bone regeneration.

Piezoelectric ceramics are piezoelectric materials with polycrystalline structure and have been widely used in many fields such as medical imaging and sound sensors. As knowledge about this kind of material develops, researchers find piezoelectric ceramics possess favorable piezoelectricity, biocompatibility, mechanical properties, porous structure and antibacterial effect and endeavor to apply piezoelectric ceramics to the field of bone tissue engineering. However, clinically no piezoelectric ceramics have been exercised so far. Therefore, in this paper we present a comprehensive review of the research and development of various piezoelectric ceramics including barium titanate, potassium sodium niobate and zinc oxide ceramics and aims to explore the application of piezoelectric ceramics in bone regeneration by providing a detailed overview of the current knowledge and research of piezoelectric ceramics in bone tissue regeneration.

Real-time monitoring of disc cutter wear in tunnel boring machines: A sound and vibration sensor-based approach with machine learning technique

Large portions of the tunnel boring machine (TBM) construction cost are attributed to disc cutter consumption, and assessing the disc cutter's wear level can help determine the optimal time to replace the disc cutter. Therefore, the need to monitor disc cutter wear in real-time has emerged as a technical challenge for TBMs. In this study, real-time disc cutter wear monitoring is developed based on sound and vibration sensors. For this purpose, the microphone and accelerometer were used to record the sound and vibration signals of cutting three different types of rocks with varying abrasions on a laboratory scale. The relationship between disc cutter wear and the sound and vibration signal was determined by comparing the measurements of disc cutter wear with the signal plots for each sample. The features extracted from the signals showed that the sound and vibration signals are impacted by the progression of disc wear during the rock-cutting process. The signal features obtained from the rock-cutting operation were utilized to verify the machine learning techniques. The results showed that the multilayer perceptron (MLP), random subspace-based decision tree (RS-DT), DT, and random forest (RF) methods could predict the wear level of the disc cutter with an accuracy of 0.89, 0.951, 0.951, and 0.927, respectively. Based on the accuracy of the models and the confusion matrix, it was found that the RS-DT model has the best estimate for predicting the level of disc wear. This research has developed a method that can potentially determine when to replace a tool and assess disc wear in real-time.

Vibration Characteristics and Frequency Modulation of Rocket Engine Multiconfiguration Small Pipeline Systems

As the important component of rocket engines, small pipeline systems have the characteristics of being lightweight and having structural complexity and obvious randomness in vibration effects. Mastering the dynamic characteristics of the pipeline systems is a key technical approach to improving the overall lifespan of engines. This study used a noncontact sound pressure sensor for dynamic parameter collection, reducing the experimental errors caused by the accelerometer’s weight and signal line interference, etc., factors. The dynamic characteristic experimental and simulation study was conducted on several types of combined configuration small pipeline systems, including plane pipelines, space pipelines, support plates, and clamps. The errors of the top six modal results were all less than 20%, with a minimum error of 0.5%, proving the correctness and effectiveness of the dynamic characteristic experimental and simulation methods. The modified modeling and FEA methods were used to study the structural optimization of pipeline systems, which can provide engine pipeline systems reasonable guidance for natural frequency modulation and parameter sensitivity results analysis.

Arduino Uno-based sound sensor system for waste sorting of metal and non-metal

Arduino Uno-based sound sensor system for waste sorting of metal and non-metal

High‐Performance Zn2+‐Crosslinked MXene Fibers for Versatile Flexible Electronics

AbstractThe advent of flexible electronics has prompted the development of functional fibers with superior mechanical and electrical properties. MXenes, a novel family of 2D functional materials, have a variety of potential applications in flexible electronics. Herein, wet‐spinning is employed to continuously assemble Ti3C2Tx MXene liquid crystals into macroscopic fibers. Meanwhile, Zn2+ is introduced into the fiber to eliminate the electrostatic repulsion between the MXene nanosheets and enhance interlayer interactions and sheet alignment. The as‐obtained MXene fibers have strong mechanical strength (150.7 MPa), high electrical conductivity (3637.9 S cm−1), and good flexibility that facilitates weaving and knotting, making them suitable for fabric‐like flexible devices. The sound pressure sensors are woven from MXene fibers, which feature quick response time (286 ms) and recovery time (642 ms), ultra‐high sensitivity (280.2 kPa−1), and a low detection limit (0.1 Pa). Sound detection and recording are achieved using this sensor. MXene fibers as wearable thermal management devices are also demonstrated, exhibiting fast Joule thermal responses and good cycling stability.

Dynamic Data-Driven degradation method for monitoring remaining useful life of cutting tools

Monitoring tool condition and remaining useful life (RUL) are vital in preventing the occurrence of excessive tool wear. This paper develops a novel dynamic data-driven degradation method for monitoring the RUL of cutting tools. In sensor-data collection, vibration, sound, and power external sensors and built-in data are gathered from the machine tool. In multi-feature selection and dynamic model updating, a decision-level fusion method of spanning multi-domain features is designed to dynamically utilize a global prediction error for selecting and fusion degradation features, which are associated with the cutting tool life in the degradation model. A rolling HI-RUL mapping is established in RUL prediction by employing a historical health indicator curve, which estimates the RUL of cutting tool with a given threshold. The effectiveness of proposed method was assessed through two run-to-failure experiments of cutting tools, showing that an average global prediction error is reduced to 4.07%.

Frequency-focused sound data generator for fault diagnosis in industrial robots

Abstract A frequency-focused sound data generator was developed for the in situ fault sound diagnosis of industrial robot reducers. The sound data generator, based on a conditional generative adversarial network, selects a target frequency range without relying on domain knowledge. A sound dataset of normal and faulty harmonic drive rotations of in situ industrial robots was collected using an attachable wireless sound sensor. The generated sound data were evaluated based on the fault diagnosis accuracy of a simple classifier trained using the generated data and tested using real data. The proposed method well-defined the frequency feature clusters and produced high-quality data, exhibiting up to 16.0% higher precision score on normal and 13.0% higher accuracy on weak-fault harmonic drive compared with the conventional methods, achieving fault diagnosis accuracy of 95.6% even in situations of fault data comprising only 5% of the normal data.

Visualization of the Proficiency Level of Assembly Work Using Inertial and Sound Sensors

Visualization of the Proficiency Level of Assembly Work Using Inertial and Sound Sensors

Design and Build Noise and CO2 Control Devices in IOT (Internet of Things) Based Libraries

The library is a source of knowledge, information, and support for learning. It is equipped with facilities to support comfort and maintain concentration while carrying out activities in the library. For human resources to progress further, libraries must be made as comfortable as possible to support learning. This study aims to design a noise and CO2 control device in an IOT (Internet of Things) based library by using 4 sound sensors KY-037 to detect noise and 1 MQ-135 sensor to detect CO2 gas. This research method uses a literature review study. The noise and CO2 control device in the IOT (Internet Of Things) based library has been completed and can work as planned, the accuracy obtained from the KY-037 sound sensor is quite high, which is 97.6%. However, the good thing is that if the sensor accuracy is improved again, the accuracy obtained from the MQ-135 sound sensor is also quite high, which is 99.16%. Conclusion If the accuracy of the sensor is improved again, the web server runs smoothly using AJAX (Asynchronous et al.) so that the resulting website does not need to load the entire page and the ESP32 as a microcontroller can control the entire system well.