Skip to main content

Advertisement

SpringerLink
Log in

Prediction of black carbon in marine engines and correlation analysis of model characteristics based on multiple machine learning algorithms

  • Research Article
  • Published:
Environmental Science and Pollution Research Aims and scope Submit manuscript

Abstract

Ship black carbon emissions have caused great harm to ecological environment. In order to estimate the black carbon emissions, thereby reducing the cost of black carbon experiments, here, we introduced four machine learning algorithms which are lasso regression, support vector machine, extreme gradient boosting, and artificial neural network to predict ship black carbon emissions. The prediction models were established with using the datasets acquired from similar marine engines under various steady-state conditions. The results show that SVM, XGB, and ANN have higher prediction accuracy than lasso regression, and the adjusted R2 of each model is 0.9810, 0.9850, 0.9885, and 0.6088. Although ANN shows the best prediction performance, it is inferior to SVM and XGB in terms of model stability and training cost. Then, in order to simplify the optimization process of hyperparameters and improve the prediction accuracy of the model at the same time, we use three different swarm intelligence algorithms to automatically optimize the hyperparameters of SVM and XGB. In addition, we applied mutual information to measure the correlation between the characteristics of the prediction models and black carbon concentration and found that the characteristics which related to in-cylinder combustion have a strong correlation with the black carbon concentration. The findings in this paper prove the feasibility of machine learning in ship black carbon emission prediction and could provide references for reducing ship black carbon emissions and the formulation of emission regulations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Similar content being viewed by others

Ethics approval and consent to participate.

Not applicable.

Data Availability

The datasets generated and analyzed during the current study are not publicly available due to the datasets are used for engine R&D and belong to the technical secret of the enterprise but are available from the corresponding author on reasonable request. The datasets used during the current study are available from the corresponding author on reasonable request.

Abbreviations

IMO:

International Maritime Organization

FSN:

Filter smoke number

PAS:

Photo-acoustic spectroscopy

LII:

Laser-induced incandescence

MAAP:

Multi-angle absorption photometer

OC:

Organic carbon

BC:

Black carbon

eBC:

Concentration of black carbon

rpm:

Engine speed (r·min−1)

ML:

Machine learning

BTDC:

Before top dead center

CA:

Crack angle

FC:

Fuel consumption

BSFC:

Brake-specific fuel consumption

MEP:

Mean effective pressure

AI:

Air intake

AMI:

Adjusted mutual information

RP:

Rail pressure

IT:

Injection timing

LR:

Load rate

φ:

Excess air coefficient

ANN:

Artificial neural network

XGB:

Extreme gradient boosting

GBDT:

Gradient boosting decision tree

SVM:

Support vector machine

R2 :

Coefficient of determination

MSE:

Mean square error

MAE:

Mean absolute error

GWO:

Gray wolf optimization

HHO:

Harris hawk optimization

SSA:

Sparrow search algorithm

MI:

Mutual information

NMI:

Normalized mutual information

References

  • Ağbulut Ü, Gürel AE, Sarıdemir S (2021) Experimental investigation and prediction of performance and emission responses of a CI engine fuelled with different metal-oxide based nanoparticles–diesel blends using different machine learning algorithms[J]. Energy 215:119076

    Article  Google Scholar 

  • Anenberg SC, Schwartz J, Shindell D et al (2012) Global air quality and health co-benefits of mitigating near-term climate change through methane and black carbon emission controls[J]. Environ Health Perspect 120(6):831–839

    Article  Google Scholar 

  • Anenberg SC, Miller J, Henze DK et al (2019) The global burden of transportation tailpipe emissions on air pollution-related mortality in 2010 and 2015[J]. Environ Res Lett 14(9):094012

    Article  CAS  Google Scholar 

  • Anenberg S, Miller J, Henze D et al (2020) A global snapshot of the air pollution-related health impacts of transportation sector emissions in 2010 and 2015 (2019) [J]

  • Azzara A, Minjares R, Rutherford D (2015) Needs and opportunities to reduce black carbon emissions from maritime shipping[J]. Assessment 118(11):5380–5552

    Google Scholar 

  • Badra J, Sim J, Pei Y et al (2020) Combustion system optimization of a light-duty GCI engine using CFD and machine learning[R]. SAE Technical Paper

  • Bansal, Jagdish Chand, Pramod Kumar Singh, Nikhil R Pal et al (2019) Evolutionary and swarm intelligence algorithms. Vol. 779. Cham: Springer

  • Belghazi M I, Baratin A, Rajeshwar S et al (2018) Mutual information neural estimation[C]//International Conference on Machine Learning. PMLR: 531–540.

  • Bellone M, Faghani E, Karayiannidis Y (2020) Comparison of CNN and LSTM for modeling virtual sensors in an engine[J]. SAE International Journal of Advances and Current Practices in Mobility 2(2020–01–0735): 2632–2639

  • Bond TC, Doherty SJ, Fahey DW et al (2013) Bounding the role of black carbon in the climate system: a scientific assessment[J]. J Geophys Res: Atmos 118(11):5380–5552

    Article  CAS  Google Scholar 

  • Bové H, Bongaerts E, Slenders E et al (2019) Ambient black carbon particles reach the fetal side of human placenta[J]. Nat Commun 10(1):1–7

    Article  Google Scholar 

  • Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system[C]//Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining: 785–794

  • Comer B (2021) Maritime Shipping: black carbon issues at the International Maritime Organization[M]//Transportation Air Pollutants. Springer, Cham, pp 13–25

    Google Scholar 

  • Corbett JJ, Lack DA, Winebrake JJ et al (2010) Arctic shipping emissions inventories and future scenarios[J]. Atmos Chem Phys 10(19):9689–9704

    Article  CAS  Google Scholar 

  • Fang XH, Papaioannou N, Leach F et al (2021) On the application of artificial neural networks for the prediction of NO x emissions from a high-speed direct injection diesel engine[J]. Int J Engine Res 22(6):1808–1824

    Article  CAS  Google Scholar 

  • Heidari AA, Mirjalili S, Faris H et al (2019) Harris hawks optimization: algorithm and applications[J]. Futur Gener Comput Syst 97:849–872

    Article  Google Scholar 

  • Herceg S, Andrijić ŽU, Bolf N (2019) Development of soft sensors for isomerization process based on support vector machine regression and dynamic polynomial models[J]. Chem Eng Res Des 149:95–103

    Article  CAS  Google Scholar 

  • IMO Secretariat, Report to the Marine Environment Protection Committee (No. PPR 5/24). International Maritime Organization (2018)

  • ISO 8178–3:2019. Reciprocating internal combustion engines — exhaust emission measurement — part 3: test procedures for measurement of exhaust gas smoke emissions from compression ignition engines using a filter type smoke meter.

  • Jaliliantabar F, Ghobadian B, Najafi G et al (2018) Artificial neural network modeling and sensitivity analysis of performance and emissions in a compression ignition engine using biodiesel fuel[J]. Energies 11(9):2410

    Article  Google Scholar 

  • Ko E, Park J (2019) Diesel mean value engine modeling based on thermodynamic cycle simulation using artificial neural network[J]. Energies 12(14):2823

    Article  CAS  Google Scholar 

  • Koschwitz D, Frisch J, Van Treeck C (2018) Data-driven heating and cooling load predictions for non-residential buildings based on support vector machine regression and NARX Recurrent Neural Network: A comparative study on district scale[J]. Energy 165:134–142

    Article  Google Scholar 

  • Kowalski J, Krawczyk B, Woźniak M (2017) Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble[J]. Eng Appl Artif Intell 57:134–141

    Article  Google Scholar 

  • Lee J, Kwon S, Kim HJ et al (2021) Machine learning applied to the NOx prediction of diesel vehicle under real driving cycle[J]. Appl Sci 11(9):3758

    Article  CAS  Google Scholar 

  • Li Y, Henze DK, Jack D et al (2016) Assessing public health burden associated with exposure to ambient black carbon in the United States[J]. Sci Total Environ 539:515–525

    Article  CAS  Google Scholar 

  • Li H, Butts K, Zaseck K et al (2017) Emissions modeling of a light-duty diesel engine for model-based control design using multi-layer perceptron neural networks[R]. SAE Technical Paper

  • Liang W, Luo S, Zhao G et al (2020) Predicting hard rock pillar stability using GBDT, XGBoost, and LightGBM algorithms[J]. Mathematics 8(5):765

    Article  Google Scholar 

  • Meilă M (2007) Comparing clusterings—an information-based distance[J]. J Multivar Anal 98(5):873–895

    Article  Google Scholar 

  • Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer[J]. Adv Eng Softw 69:46–61

    Article  Google Scholar 

  • Momenimovahed A, Gagné S, Martens P et al (2021) Comparison of black carbon measurement techniques for marine engine emissions using three marine fuel types[J]. Aerosol Science and Technology (just-accepted): 1–19

  • Newman MEJ, Cantwell GT, Young JG (2020) Improved mutual information measure for clustering, classification, and community detection[J]. Phys Rev E 101(4):042304

    Article  CAS  Google Scholar 

  • Niu X, Yang C, Wang H et al (2017) Investigation of ANN and SVM based on limited samples for performance and emissions prediction of a CRDI-assisted marine diesel engine[J]. Appl Therm Eng 111:1353–1364

    Article  Google Scholar 

  • Özener O, Yüksek L, Özkan M (2013) Artificial neural network approach to predicting engine-out emissions and performance parameters of a turbo charged diesel engine[J]. Therm Sci 17(1):153–166

    Article  Google Scholar 

  • Ramanathan V, Carmichael G (2008) Global and regional climate changes due to black carbon[J]. Nat Geosci 1(4):221–227

    Article  CAS  Google Scholar 

  • Ranstam J, Cook JA (2018) LASSO regression[J]. J Br Surg 105(10):1348–1348

    Article  Google Scholar 

  • Rasmussen MA, Bro R (2012) A tutorial on the Lasso approach to sparse modeling[J]. Chemom Intell Lab Syst 119:21–31

    Article  CAS  Google Scholar 

  • Renault T (2020) Sentiment analysis and machine learning in finance: a comparison of methods and models on one million messages[J]. Digital Finance 2(1):1–13

    Article  Google Scholar 

  • Taghavifar H, Taghavifar H, Mardani A et al (2014) Exhaust emissions prognostication for DI diesel group-hole injectors using a supervised artificial neural network approach[J]. Fuel 125:81–89

    Article  CAS  Google Scholar 

  • Tahsien SM, Karimipour H, Spachos P (2020) Machine learning based solutions for security of Internet of Things (IoT): A survey[J]. J Netw Comput Appl 161:102630

    Article  Google Scholar 

  • Tibshirani R (1996) Regression shrinkage and selection via the lasso[J]. J Roy Stat Soc: Ser B (methodol) 58(1):267–288

    Google Scholar 

  • Timonen H, Aakko-Saksa P, Kuittinen N et al (2017) Black carbon measurement validation onboard (SEA-EFFECTS BC WP2) [J]. SEA EFFECTS BC WP2, SEA-EFFECTS PROJECT

  • Viana M, Hammingh P, Colette A et al (2014) Impact of maritime transport emissions on coastal air quality in Europe[J]. Atmos Environ 90:96–105

    Article  CAS  Google Scholar 

  • Vinh NX, Epps J, Bailey J (2010) Information theoretic measures for clusterings comparison: variants, properties, normalization and correction for chance[J]. The Journal of Machine Learning Research 11:2837–2854

    Google Scholar 

  • Werbos P (1974) Beyond regression: new tools for prediction and analysis in the behavior science[J]. Unpublished Doctoral Dissertation, Harvard University

  • Wilkinson J, Arnold K F, Murray EJ et al (2020) Time to reality check the promises of machine learning-powered precision medicine[J]. The Lancet Digital Health

  • Xu X, Zhao Z, Xu X et al (2020) Machine learning-based wear fault diagnosis for marine diesel engine by fusing multiple data-driven models[J]. Knowl-Based Syst 190:105324

    Article  Google Scholar 

  • Xue J, Shen B (2020) A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering 8(1):22–34

    Article  Google Scholar 

  • Yu C, Seslija M, Brownbridge G et al (2020) Deep kernel learning approach to engine emissions modeling[J]. Data-Centric Engineering 1

Download references

Acknowledgements

The authors are thankful to all the personnel who either provided technical support or helped with data collection. We also acknowledge all the reviewers for their useful comments and suggestions.

Author information

Authors and Affiliations

  1. School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan, Hubei, 430070, People’s Republic of China

    Ying Sun, Lin Lü, Yun-kai Cai & Peng Lee

Authors
  1. Ying Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lin Lü
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yun-kai Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peng Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Ying Sun, conceptualization, data curation, formal analysis, investigation, methodology, software, writing — original draft, and visualization.

Lin Lü, conceptualization, methodology, investigation, resources, writing — review and editing, supervision, and project administration.

Yun-kai Cai, writing — review and editing.

Peng Lee, conceptualization, methodology, validation, and writing — review and editing.

Corresponding author

Correspondence to Peng Lee.

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Responsible Editor: Philippe Garrigues

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sun, Y., Lü, L., Cai, Yk. et al. Prediction of black carbon in marine engines and correlation analysis of model characteristics based on multiple machine learning algorithms. Environ Sci Pollut Res 29, 78509–78525 (2022). https://doi.org/10.1007/s11356-022-20496-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11356-022-20496-4

Keywords

Search

Navigation