Skip to main content
Springer Nature Link
Log in

Neural-network-based interval grey prediction models with applications to forecasting the demand of printed circuit boards

  • Application of soft computing
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Forecasting the demand of product materials required for industries can help practitioner to formulate financial and marketing strategies. Available data are often nonlinear and real-valued, but samples are often derived from uncertain assessments, without adhering to any statistical assumptions. Furthermore, to provide the degree of variation associated with forecasts, it is preferable to estimate an interval consisting of the upper and lower bounds, rather than a single predicted value at each time period. Although non-statistical grey prediction is appropriate in such situations, previous interval grey prediction models were bounded. This study thus develops a neural-network-based interval grey prediction model and focus on the evaluation of the reliability of estimated intervals. In light of the importance of printed circuit boards (PCBs) to the manufacture of electrical and electronic products, the performance of the proposed model was verified by forecasting PCB product values. The results show that the proposed model performs well among considered interval grey prediction models.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The data that support the findings of this study are available from the Prismark statistics.

References

  • Angrist JD (2003) Fundamentals of artificial neural networks. The MIT Press, Cambridge, MA, A Bradford Book

    Google Scholar 

  • Cankurt S, Subasi A (2015) Developing tourism demand forecasting models using machine learning techniques with trend, seasonal, and cyclic components. BALKAN J Elect Comput Eng 3(1):42–49

    Google Scholar 

  • Chatfield C (2016) The analysis of time series: an introduction. CRC Press, London

    MATH  Google Scholar 

  • Chen Y, He K, Zhang C (2016) A novel gray wave forecasting method for predicting metal prices. Resour Policy 49:323–331

    Article  Google Scholar 

  • Chen YY, Liu HT, Hsieh HL (2019) Time series interval forecast using GM(1,1) and NGBM(1, 1) models. Soft Comput 23:1541–1555

    Article  Google Scholar 

  • Ding S, Li R (2021) Forecasting the sales and stock of electric vehicles using a novel self-adaptive optimized gray model. Eng Appl Artif Intell. https://doi.org/10.1016/j.engappai.2020.104148

    Article  Google Scholar 

  • Ding S, Li R, Wu S (2021a) A novel composite forecasting framework by adaptive data preprocessing and optimized nonlinear gray Bernoulli model for new energy vehicles sales. Commun Nonlinear Sci Numer Simul. https://doi.org/10.1016/j.cnsns.2021.105847

    Article  MATH  Google Scholar 

  • Ding S, Li R, Tao Z (2021b) A novel adaptive discrete gray model with time-varying parameters for long-term photovoltaic power generation forecasting. Energy Convers Manag. https://doi.org/10.1016/j.enconman.2020.113644

    Article  Google Scholar 

  • Ding S, Li R, Wu S, Zhou W (2021c) Application of a novel structure-adaptative gray model with adjustable time power item for nuclear energy consumption forecasting. Appl Energy. https://doi.org/10.1016/j.apenergy.2021.117114

    Article  Google Scholar 

  • Forward Business Information (2019), Report of market perspective and investment strategy planning on China Printed circuit board manufacturing industry (2019–2024), Technical Report No. IM38229, iiMedia Research, Hong Kong, China.

  • Hu YC (2009) Functional-link nets with genetic-algorithm-based learning for robust nonlinear interval regression analysis. Neurocomputing 72:1808–1816

    Article  Google Scholar 

  • Hu YC (2017) Electricity consumption forecasting using a neural-network-based gray prediction approach. J Op Res Soc 68(10):1259–1264

    Article  Google Scholar 

  • Hu YC (2020) Energy demand forecasting using a novel remnant GM(1,1) model. Soft Comput 24:13903–13912

    Article  Google Scholar 

  • Hu Z, Gao C, Su Q (2021) A novel evolutionary algorithm based on even difference gray model. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2021.114898

    Article  Google Scholar 

  • Huang YL, Lin CT (2011) Developing an interval forecasting method to predict undulated demand. Qual Quant 45:513–524

    Article  Google Scholar 

  • Huang L, Zhang BL, Huang Q (1998) Robust interval regression analysis using neural networks. Fuzzy Sets Syst 97:337–347

    Article  Google Scholar 

  • Hwang C, Hong DH, Seok KH (2006) Support vector interval regression machine for crisp input and output data. Fuzzy Sets Syst 157:1114–1125

    Article  MathSciNet  Google Scholar 

  • Intelligence Research (2018), 2019–2025 Annual research and consultation report of panorama survey and development strategy on China PCB industry, Technical Report No. R689087, Intelligence Research Group, Beijing, China.

  • Ishibuchi H, Tanaka H (1992) Fuzzy regression analysis using neural networks. Fuzzy Sets Syst 50:257–265

    Article  MathSciNet  Google Scholar 

  • Ishibuchi H, Nii M (2001) Fuzzy regression using asymmetric fuzzy coefficients and fuzzified neural networks. Fuzzy Sets Syst 119:273–290

    Article  MathSciNet  Google Scholar 

  • Jeng JT, Chuang CC, Su SF (2003) Support vector interval regression networks for interval regression analysis. Fuzzy Sets Syst 138:283–300

    Article  MathSciNet  Google Scholar 

  • Lee YC, Wu CH, Tsai SB (2014) Gray system theory and fuzzy time series forecasting for the growth of green electronic materials. Int J Prod Res 52:2931–2945

    Article  Google Scholar 

  • Li K, Liu L, Zhai J, Khoshgoftaar TM, Li T (2016) The improved gray model based on particle swarm optimization algorithm for time series prediction. Eng Appl Artif Intell 55:285–291

    Article  Google Scholar 

  • Li G, Wu C, Zhou M, Liu A (2019) The combination of interval forecasts in tourism. Ann Tour Res 75:363–378

    Article  Google Scholar 

  • Liu S, Lin Y (2010) Gray information: theory and practical applications. Springer-Verlag, London

    Google Scholar 

  • Liu S, Yang Y, Forrest J (2017), Gray data analysis: methods, models and applications, Springer, Berlin.

  • Marques AC, Cabrera JM, Malfatti CF (2013) Printed circuit boards: a review on the perspective of sustainability. J Environ Manag 131:298–306

    Article  Google Scholar 

  • Qiu RTR, Wu DC, Dropsy V, Petit S, Pratt S, Ohe Y (2021) Visitor arrivals forecasts amid COVID-19: a perspective from the Asia and Pacific team. Ann Tour Res. https://doi.org/10.1016/j.annals.2021.103155

    Article  Google Scholar 

  • Shih CS, Hsu YT, Yeh J, Lee YP (2011) Gray number prediction using the gray modification model with progression technique. Appl Math Model 35(3):1314–1321

    Article  MathSciNet  Google Scholar 

  • Suganthi L, Samuel AA (2012) Energy models for demand forecasting-A review. Renew Sustain Energy Rev 16:1223–1240

    Article  Google Scholar 

  • Sun W, Xu Y (2017) Research on China’s energy supply and demand using an improved gray-Markov chain model based on wavelet transform. Energy 118:969–984

    Article  Google Scholar 

  • Tan PN, Steinbach M, Kumar V (2005) Introduction to data mining, pearson addison Wesley, Boston.

  • Tanaka H (1987) Fuzzy data analysis by possibilistic linear models. Fuzzy Sets Syst 24:363–375

    Article  MathSciNet  Google Scholar 

  • Tanaka H, Uejima S, Asai K (1982) Linear regression analysis with fuzzy model. IEEE Trans Syst Man Cybern 12:903–907

    Article  Google Scholar 

  • Toksari MD (2009) Estimating the net electricity energy generation and demand using ant colony optimization approach: case of Turkey. Energy Policy 37:1181–1187

    Article  Google Scholar 

  • Taiwan Printed Circuit Association (2019), The gaps of technical blueprint of Taiwan printed circuit boards, Printed Circuit Boards Quarterly, No. 84.

  • Tutun S, Chou CA, Canıyılmaz E (2015) A new forecasting framework for volatile behavior in net electricity consumption: a case study in Turkey. Energy 93:2406–2422

    Article  Google Scholar 

  • Wang ZX, Jv YQ (2021) A non-linear systematic gray model for forecasting the industrial economy-energy-environment system. Technol Forecast Soc Chang. https://doi.org/10.1016/j.techfore.2021.120707

    Article  Google Scholar 

  • Xia C, Wang J, McMenemy KS (2010) Medium and long term load forecasting model and virtual load forecaster based on radial basis function neural networks. Electr Power Energy Syst 32:743–750

    Article  Google Scholar 

  • Xie N, Liu S, Yuan C, Yang Y (2014) Gray number sequence forecasting approach for interval analysis: a case of China’s gross domestic product prediction. J gray Syst 26(1):45–58

    Google Scholar 

  • Xu N, Dang Y, Gong Y (2017) Novel gray prediction model with nonlinear optimized time response method for forecasting of electricity consumption in China. Energy 118:473–480

    Article  Google Scholar 

  • Zeng B, Li C, Zhou XY, Long XJ (2014) Prediction model of interval gray number with a real parameter and its application. Abstr Appl Anal. https://doi.org/10.1155/2014/939404

    Article  Google Scholar 

  • Zeng B, Liu SF, Xie NM, Cui J (2010) Prediction model for interval gray number based on gray band and gray layer. Control and Decision 25(10):1585–1592

    Google Scholar 

  • Zhao H, Guo S (2016) An optimized gray model for annual power load forecasting. Energy 107:272–286

    Article  Google Scholar 

Download references

Funding

This research is supported by the Ministry of Science and Technology, Taiwan under grant MOST 110–2410–H–033–013–MY2.

Author information

Authors and Affiliations

  1. Department of Business Administration, Chung Yuan Christian University, Taoyuan City, Taiwan

    Yi-Chung Hu

Authors
  1. Yi-Chung Hu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Yi-Chung Hu.

Ethics declarations

Conflict of interest

The author declares that they have no conflict of interest.

Human and animal participants

This article does not contain any studies with human participants or animals performed by the author.

Additional information

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

Hu, YC. Neural-network-based interval grey prediction models with applications to forecasting the demand of printed circuit boards. Soft Comput 26, 11827–11838 (2022). https://doi.org/10.1007/s00500-022-06963-7

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-022-06963-7

Keywords