Soft sensor for the prediction of oxygen content in boiler flue gas using neural networks and extreme gradient boosting

Kurniawan, Eko David; Effendy, Nazrul; Arif, Agus; Dwiantoro, Kenny; Muddin, Nidlom

doi:10.1007/s00521-022-07771-8

Cited by 10 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Salah satu pendekatan populer yang diyakini bisa menyelesaikan berbagai masalah dalam deteksi adalah dengan teknik dan aplikasi jaringan saraf tiruan (JST) [4]- [7]. JST telah semakin banyak dieksplorasi selama dua dekade terakhir termasuk di proses industri.…”

Section: Pendahuluanunclassified

Deteksi Osilasi Kontrol Proses Industri dengan Menggunakan Jaringan Saraf Tiruan - Review

Tsanya

Wardana

Effendy

2022

jeeccis

View full text Add to dashboard Cite

Osilasi kontrol loop adalah salah satu masalah yang sering terjadi di proses industri. Osilasi menyebabkan variabel proses tidak dapat dipertahankan pada kondisi yang diinginkan yang akan menyebabkan kerugian finansial pada industri. Selama beberapa tahun terakhir sudah banyak penelitian yang dilakukan, dan salah satu pendekatan yang semakin banyak digunakan adalah menggunakan jaringan saraf tiruan (JST). Tulisan ini memberikan gambaran tentang karakterisktik JST dan penerapannya untuk deteksi dan diagnosis osilasi kontrol pada proses industri. Dari beberapa studi yang dipelajari, arsitektur JST yang paling umum dipilih untuk proses deteksi osilasi adalah multilayer perceptron (MLP), convulational neural network (CNN) dan recurrent neural network (RNN). Tiap arsitektur tersebut memiliki karakteristik dan fungsi yang berbeda. MLP memiliki karakteristik yang sederhana, dan fleksibel dibandingkan jaringan lainnya. CNN bekerja sangat baik untuk melakukan teknik deteksi dengan menggunakan pengenalan pola. Sementara RNN sangat baik digunakan untuk mendeteksi sistem dinamis pada proses industri.

show abstract

Section: Pendahuluanunclassified

Deteksi Osilasi Kontrol Proses Industri dengan Menggunakan Jaringan Saraf Tiruan - Review

Tsanya

Wardana

Effendy

2022

jeeccis

View full text Add to dashboard Cite

show abstract

“…Furthermore, by integrating the BPNN and the genetic algorithm (GA), a soft measurement approach for measuring the oxygen content in a power plant's flue gas was proposed [16]. A method combining extreme gradient boosting (XGBoost) and ANN was proposed to predict the oxygen content in boilers [17]. By implementing the aforementioned method, satisfactory experimental results could be obtained via effective measurement of the oxygen content in the flue gas.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Soft Sensor Model for Measuring the Oxygen Content in Boiler Flue Gas

Wang,

Li,

Zhang

2024

Sensors

View full text Add to dashboard Cite

As an indispensable component of coal-fired power plants, boilers play a crucial role in converting water into high-pressure steam. The oxygen content in the flue gas is a crucial indicator, which indicates the state of combustion within the boiler. The oxygen content not only affects the thermal efficiency of the boiler and the energy utilization of the generator unit, but also has adverse impacts on the environment. Therefore, accurate measurement of the flue gas’s oxygen content is of paramount importance in enhancing the energy utilization efficiency of coal-fired power plants and reducing the emissions of waste gas and pollutants. This study proposes a prediction model for the oxygen content in the flue gas that combines the whale optimization algorithm (WOA) and long short-term memory (LSTM) networks. Among them, the whale optimization algorithm (WOA) was used to optimize the learning rate, the number of hidden layers, and the regularization coefficients of the long short-term memory (LSTM). The data used in this study were obtained from a 350 MW power generation unit in a coal-fired power plant to validate the practicality and effectiveness of the proposed hybrid model. The simulation results demonstrated that the whale optimization algorithm–long short-term memory (WOA-LSTM) model achieved an MAE of 0.16493, an RMSE of 0.12712, an MAPE of 2.2254%, and an R2 value of 0.98664. The whale optimization algorithm–long short-term memory (WOA-LSTM) model demonstrated enhancements in accuracy compared with the least squares support vector machine (LSSVM), long short-term memory (LSTM), particle swarm optimization–least squares support vector machine (PSO-LSSVM), and particle swarm optimization–long short-term memory (PSO-LSTM), with improvements of 4.93%, 4.03%, 1.35%, and 0.49%, respectively. These results indicated that the proposed soft sensor model exhibited more accurate performance, which can meet practical requirements of coal-fired power plants.

show abstract

“…Recently, the rapid development of deep learning and image processing methods has brought great changes to the industry. − Compared with the various limitations of physical measurement instruments, deep-learning-based soft measurement technology of combustion oxygen content is becoming a hot topic for researchers. The input data to the soft sensors in refs − are the process variables of the combustion system. This requires the construction of data sets by combining measurements from multiple sensors.…”

Section: Introductionmentioning

confidence: 99%

Online Estimation of Combustion Oxygen Content with an Image-Augmented Soft Sensor Using Imbalanced Flame Images

Gao,

Liu,

Jiang

et al. 2023

ACS Omega

View full text Add to dashboard Cite

High-accuracy oxygen content measurement and control is one key to improving combustion efficiency and economic efficiency. The soft measurement technique of the oxygen content based on flame images is promising. However, image feature acquisition at different oxygen contents and image generation under unbalanced conditions are still challenging. To relieve this dilemma, a new generative-based regression model is developed. It not only learns the potential vectors but also captures flame features well to generate virtually high-quality-labeled flame images. The training data sets can be augmented, thus saving a lot of data collection experiments. Subsequently, a convolutional-based regression model is constructed to estimate the oxygen content using the augmented flame images directly. The designed method generates informative flame images and obtains more accurate oxygen content estimation results than several common methods.

show abstract

Soft sensor for the prediction of oxygen content in boiler flue gas using neural networks and extreme gradient boosting

Cited by 10 publications

References 44 publications

Deteksi Osilasi Kontrol Proses Industri dengan Menggunakan Jaringan Saraf Tiruan - Review

Deteksi Osilasi Kontrol Proses Industri dengan Menggunakan Jaringan Saraf Tiruan - Review

A Hybrid Soft Sensor Model for Measuring the Oxygen Content in Boiler Flue Gas

Online Estimation of Combustion Oxygen Content with an Image-Augmented Soft Sensor Using Imbalanced Flame Images

Contact Info

Product

Resources

About