Development of Predictive Emissions Monitoring System Using Open Source Machine Learning Library – Keras: A Case Study on a Cogeneration Unit

Si, Minxing; Tarnoczi, Tyler J.; Wiens, Brett M.; Du, Ke

doi:10.1109/access.2019.2930555

Cited by 33 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PM 2.5 measured by the SHARP instrument is used as the target to supervise the machine-learning process. The processed dataset, with 3050 rows and four columns, was randomly shuffled and then divided into a training set, which was composed of the data used to build models and minimize the loss function, and a test set, which was composed of the data that the model had never been run with before testing (Si et al, 2019). The test dataset was only used once and gave an unbiased evaluation of the final model's performance.…”

Section: Calibrationmentioning

confidence: 99%

“…In addition, the sparsely spread stations may only represent PM levels in limited areas near the stations because PM concentrations vary spatially and temporally depending on local emission sources as well as meteorological conditions (Xiong et al, 2017). Such a low-resolution PM monitoring network cannot support public exposure and health effects studies that are related to PM because these studies require high-spatial-and temporal-resolution monitoring networks in the community (Snyder et al, 2013). In addition, the well-characterized scientific PM monitors are not portable due to their large size and volumetric flow rate, which means they are not practical for measuring personal PM exposure (White et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Ying

et al. 2020

Atmos. Meas. Tech.

Self Cite

View full text Add to dashboard Cite

Abstract. Particle sensing technology has shown great potential for monitoring particulate matter (PM) with very few temporal and spatial restrictions because of its low cost, compact size, and easy operation. However, the performance of low-cost sensors for PM monitoring in ambient conditions has not been thoroughly evaluated. Monitoring results by low-cost sensors are often questionable. In this study, a low-cost fine particle monitor (Plantower PMS 5003) was colocated with a reference instrument, the Synchronized Hybrid Ambient Real-time Particulate (SHARP) monitor, at the Calgary Varsity air monitoring station from December 2018 to April 2019. The study evaluated the performance of this low-cost PM sensor in ambient conditions and calibrated its readings using simple linear regression (SLR), multiple linear regression (MLR), and two more powerful machine-learning algorithms using random search techniques for the best model architectures. The two machine-learning algorithms are XGBoost and a feedforward neural network (NN). Field evaluation showed that the Pearson correlation (r) between the low-cost sensor and the SHARP instrument was 0.78. The Fligner and Killeen (F–K) test indicated a statistically significant difference between the variances of the PM2.5 values by the low-cost sensor and the SHARP instrument. Large overestimations by the low-cost sensor before calibration were observed in the field and were believed to be caused by the variation of ambient relative humidity. The root mean square error (RMSE) was 9.93 when comparing the low-cost sensor with the SHARP instrument. The calibration by the feedforward NN had the smallest RMSE of 3.91 in the test dataset compared to the calibrations by SLR (4.91), MLR (4.65), and XGBoost (4.19). After calibrations, the F–K test using the test dataset showed that the variances of the PM2.5 values by the NN, XGBoost, and the reference method were not statistically significantly different. From this study, we conclude that a feedforward NN is a promising method to address the poor performance of low-cost sensors for PM2.5 monitoring. In addition, the random search method for hyperparameters was demonstrated to be an efficient approach for selecting the best model structure.

show abstract

Section: Calibrationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Ying

et al. 2020

Atmos. Meas. Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The PM2.5 measured by the SHARP instrument is used as the target to supervise the machine learning process. The processed dataset with 3,050 rows and four columns was randomly shuffled and then divided into a training set, which was the data used to build models and minimize the loss function, and a test set, which was the data that the model has never run with before testing (Si et al, 2019). The test dataset was only used once and gave an unbiased evaluation of the final model's performance.…”

Section: Calibrationmentioning

confidence: 99%

Evaluation and Calibration of a Low-cost Particle Sensor in Ambient Conditions Using Machine Learning Technologies

Si¹,

Xiong²,

Du³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract. Particle sensing technology has shown great potential for monitoring particulate matter (PM) with very few temporal and spatial restrictions because of low-cost, compact size, and easy operation. However, the performance of low-cost sensors for PM monitoring in ambient conditions has not been thoroughly evaluated. Monitoring results by low-cost sensors are often questionable. In this study, a low-cost fine particle monitor (Plantower PMS 5003) was co-located with a reference instrument, named Synchronized Hybrid Ambient Real-time Particulate (SHARP) monitor, in Calgary Varsity air monitoring station from December 2018 to April 2019. The study evaluated the performance of this low-cost PM sensor in ambient conditions and calibrated its readings using simple linear regression (SLR), multiple linear regression (MLR), and two more powerful machine learning algorithms using random search techniques for the best model architectures. The two machine learning algorithms are XGBoost and feedforward neural network (NN). Field evaluation showed that the Pearson r between the low-cost sensor and the SHAPR instrument was 0.78. Fligner and Killeen (F-K) test indicated a statistically significant difference between the variances of the PM2.5 values by the low-cost sensor and by the SHARP instrument. Large overestimations by the low-cost sensor before calibration were observed in the field and were believed to be caused by the variation of ambient relative humidity. The root mean square error (RMSE) was 9.93 when comparing the low-cost sensor with the SHARP instrument. The calibration by the feedforward NN had the smallest RMSE of 3.91 in the test dataset, compared to the calibrations by SLR (4.91), MLR (4.65), and XGBoost (4.19). After calibrations, the F-K test using the test dataset showed that the variances of the PM2.5 values by the NN and the XGBoost and by the reference method were not statistically significantly different. From this study, we conclude that feedforward NN is a promising method to address the poor performance of the low-cost sensors for PM2.5 monitoring. In addition, the random search method for hyperparameters was demonstrated to be an efficient approach for selecting the best model structure.

show abstract

“…Thus it is crucial to monitor and predict the efficiency of the boiler which is determined by steam production rates, measuring the gas consumption rates, and performing combustion analysis. However, the prediction of boiler performance is a complex function to model because of the constantly changing characteristics of boilers over prolonged periods of its operation [2], [3]. In recent years, several researchers have worked on applying Machine Learning (ML) algorithms successfully in several applications such as weather prediction, industrial automation, vehicular area networks, Internet of Things (IoT), healthcare, and many others [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Performance Prediction and Interpretation of a Refuse Plastic Fuel Fired Boiler

Shaha¹,

Singamsetti

Tripathy

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In order to cater to the energy requirement in the form of steam at a reasonable cost, the process industries are relying on the waste incineration plants by engaging themselves through industry symbiosis. However, before the establishment of industrial symbiosis, it is very crucial to monitor and predict the operational performance of the boiler used in the waste incineration plants. The existing works focus on using Artificial Neural Networks (ANNs) for prediction of the performance of the boiler in terms of pressure, temperature, and mass flow rate of steam using the input parameters viz. feed water temperature, feed water pressure, incinerator exit temperature and conveyor speed. However, the problem with this approach is that shallow ANNs cannot model the complex mathematical non-linear relationships so precisely. In addition, ANNs are not interpretable which makes stakeholders apprehensive to use these networks in production. In this paper, we address these drawbacks of ANNs by modeling the complex relationship governing the boiler performance by using a set of machine learning and deep learning models. Also, the research paper introduces multiple techniques like feature importance, Partial Dependence Plots(PDP) plots etc. which interpret the reason behind the model's output to make it more reliable for the stakeholders. It has been empirically shown that the new Machine Learning and Deep Learning models performed better than the ANNs for predicting the boiler performance. The Random Forest model made a Mean Absolute Percentage Error (MAPE) of 1.12 and LSTMs had a MAPE of 1.14 in the prediction of steam temperature C o which is a significant improvement in comparison to the original ANN model which had a MAPE of 6.93. In the case of the predictions for steam pressure kgf /cm 2 the MAPE for the Random Forest model and LSTM was 5.54 and 4.21 respectively as compared to ANNs MAPE of 1.49. Similarly for steam mass flow rate(t/h), the MAPE was improved to 15.6 and 9.63 by Random Forest Model and LSTM respectively, which was originally 18.77 for ANN based model. These results clearly show that LSTM based models outperformed ANNs and Random Forests in terms of prediction accuracy.

show abstract

Development of Predictive Emissions Monitoring System Using Open Source Machine Learning Library – Keras: A Case Study on a Cogeneration Unit

Cited by 33 publications

References 23 publications

Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods

Evaluation and Calibration of a Low-cost Particle Sensor in Ambient Conditions Using Machine Learning Technologies

Performance Prediction and Interpretation of a Refuse Plastic Fuel Fired Boiler

Contact Info

Product

Resources

About