Inline Measurement of Particle Concentrations in Multicomponent Suspensions using Ultrasonic Sensor and Least Squares Support Vector Machines

Zhan, Xueying; Jiang, Shulan; Yang, Yili; Jiang, Liang; Shi, Tielin; Li, Xiwen

doi:10.3390/s150924109

Cited by 14 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following features were calculated from the obtained US waveform to use in the ML models. These are common features extracted from US waveforms [29]. The theory behind the selection of each feature is presented in their respective sections.…”

Section: Ultrasonic Wave Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning

et al. 2021

View full text Add to dashboard Cite

Beer fermentation is typically monitored by periodic sampling and off-line analysis. In-line sensors would remove the need for time-consuming manual operation and provide real-time evaluation of the fermenting media. This work uses a low-cost ultrasonic sensor combined with machine learning to predict the alcohol concentration during beer fermentation. The highest accuracy model (R2 = 0.952, mean absolute error (MAE) = 0.265, mean squared error (MSE) = 0.136) used a transmission-based ultrasonic sensing technique along with the measured temperature. However, the second most accurate model (R2 = 0.948, MAE = 0.283, MSE = 0.146) used a reflection-based technique without the temperature. Both the reflection-based technique and the omission of the temperature data are novel to this research and demonstrate the potential for a non-invasive sensor to monitor beer fermentation.

show abstract

Section: Ultrasonic Wave Featuresmentioning

confidence: 99%

“…where E is the waveform energy, A i is the waveform amplitude at sample point i, and start and end denote the range of samples points for the reflection of interest [29]. The peak-to-peak amplitude, maximum amplitude, and minimum amplitude provide additional information as to how the energy is distributed in the waveform.…”

Section: Energymentioning

confidence: 99%

Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…where SAA is the sum absolute amplitude, SP is the total number of sample points, and A i is the amplitude at sample point i [34].…”

Section: Machine Learning Model Development Feature Engineeringmentioning

confidence: 99%

“…Ultrasonic measurements have been combined with shallow ML algorithms such as Artificial Neural Networks (ANNs) [22][23][24][25][26][27][28][29] and Support Vector Machines (SVMs) [23,25,30,31], using waveform features from the time domain [23,25,27,31,32] and frequency domain [24,27,31,32] after analyses such as wavelet transforms [22,24]. These have been used for applications such as predicting sugar concentration during fermentation [33], measuring particle concentration in multicomponent suspensions [34], and classification of heat exchanger fouling in the dairy industry [23,25]. There are no examples of using ultrasonic measurements and ML to follow a mixing process; however, El-Hagrasy et al [35] used the Soft Independent Modelling of Class Analogies (SIMCA) and Principal Component Modified Bootstrap Error-adjusted Single-sample Technique (PC-MBEST) algorithms to analyse NIRS spectra during pharmaceutical solids blending.…”

Section: Introductionmentioning

confidence: 99%

Monitoring Mixing Processes Using Ultrasonic Sensors and Machine Learning

Bowler

Bakalis

Watson

2020

Sensors

View full text Add to dashboard Cite

Mixing is one of the most common processes across food, chemical, and pharmaceutical manufacturing. Real-time, in-line sensors are required for monitoring, and subsequently optimising, essential processes such as mixing. Ultrasonic sensors are low-cost, real-time, in-line, and applicable to characterise opaque systems. In this study, a non-invasive, reflection-mode ultrasonic measurement technique was used to monitor two model mixing systems. The two systems studied were honey-water blending and flour-water batter mixing. Classification machine learning models were developed to predict if materials were mixed or not mixed. Regression machine learning models were developed to predict the time remaining until mixing completion. Artificial neural networks, support vector machines, long short-term memory neural networks, and convolutional neural networks were tested, along with different methods for engineering features from ultrasonic waveforms in both the time and frequency domain. Comparisons between using a single sensor and performing multisensor data fusion between two sensors were made. Classification accuracies of up to 96.3% for honey-water blending and 92.5% for flour-water batter mixing were achieved, along with R2 values for the regression models of up to 0.977 for honey-water blending and 0.968 for flour-water batter mixing. Each prediction task produced optimal performance with different algorithms and feature engineering methods, vindicating the extensive comparison between different machine learning approaches.

show abstract

“…31 As the RMSE shows the residual error, it provides a good estimate of the difference between the LS-SVM predicted values and the actual values. 32 RMSE can be described as…”

Section: Least Squares-support Vector Machinesmentioning

confidence: 99%

Prediction of leak flow rate in plastic water distribution pipes using vibro-acoustic measurements

Butterfield

Meruane

Collins

et al. 2017

Structural Health Monitoring

View full text Add to dashboard Cite

Leakage from water distribution systems is a worldwide issue with consequences including loss of revenue, health and environmental concerns. Leaks have typically been found through leak noise correlation by placing sensors either side of the leak and recording and analysing its vibro-acoustic emission. While this method is widely used to identify the location of the leak, the sensors also record data that could be related to the leak's flow rate, yet no reliable method exists to predict leak flow rate in water distribution pipes using vibro-acoustic emission. The aim of this research is to predict leak flow rate in medium-density polyethylene pipe using vibro-acoustic emission signals. A novel experimental methodology is presented whereby circular holes of four sizes are tested at several leak flow rates. Following the derivation of a number of features, least squares support vector machines are used in order to predict leak flow rate. The results show a strong correlation highlighting the potential of this technique as a rapid and practical tool for water companies to assess and prioritise leak repair.

show abstract

Inline Measurement of Particle Concentrations in Multicomponent Suspensions using Ultrasonic Sensor and Least Squares Support Vector Machines

Cited by 14 publications

References 30 publications

Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning

Predicting Alcohol Concentration during Beer Fermentation Using Ultrasonic Measurements and Machine Learning

Monitoring Mixing Processes Using Ultrasonic Sensors and Machine Learning

Prediction of leak flow rate in plastic water distribution pipes using vibro-acoustic measurements

Contact Info

Product

Resources

About