# Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Preparation of Data for Analysis

## 3. Statistical Analysis

## 4. Analysis with the Use of Neural Networks

- variant 1: analysis of all available data, two measurement cycles of each parameter set go to the training set, one cycle to the test set. The number of training and test sets was 1578 and 789.
- variant 2: analysis of data obtained in the measurements with the best possible sets of parameters (Table 1), two measurement cycles of each of the included parameter sets go to the training set, one cycle to the test set. The number of training and test sets was 462 and 231.

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Jurdziak, L.; Błażej, R.; Burduk, A.; Bajda, M.; Kirjanów-Błażej, A.; Kozłowski, T.; Olchówka, D. Optimization of the operating costs of conveyor beltsin a mine in various strategies of their replacement and diagnostics. Transp. Przemysłowy Masz. Rob.
**2020**, 4, 14–22. [Google Scholar] - Webb, C.; Sikorska, J.; Khan, R.N.; Hodkiewicz, M. Developing and evaluating predictive conveyor belt wear models. Data-Cent. Eng.
**2020**, 1, e3. [Google Scholar] [CrossRef] - Barry, B. Multi-Channel Conveyor Belt Condition Monitoring. U.S. Patent 7,275,637, 2 October 2007. [Google Scholar]
- Błażej, R. Assessment of the Technical Condition of Conveyor Belts with Steel Cords; Oficyna Wydawnicza Politechniki Wrocławskiej: Wrocław, Poland, 2018. (In Polish) [Google Scholar]
- Kwaśniewski, J. Magnetic Testing of Steel Ropes—Personnel Certification System in the MTR Method; Wydawnictwa AGH: Kraków, Poland, 2010. (In Polish) [Google Scholar]
- Kwaśniewski, J.; Machula, T. Diagnostics of belts with steel cords. Transp. Przemysłowy
**2006**, 4, 22–24. (In Polish) [Google Scholar] - Błażej, R.; Jurdziak, L.; Kirjanów, A.; Kozłowski, T. Evaluation of the quality of steel cord belt splices based on belt condition examination using magnetic techniques. Diagnostyka
**2015**, 16, 59–64. [Google Scholar] - Błażej, R.; Jurdziak, L.; Kozłowski, T.; Kirjanów, A. The use of magnetic sensors in monitoring the condition of the core in steel cord conveyor belts—Tests of the measuring probe and the design of the DiagBelt system. Measurement
**2018**, 123, 48–53. [Google Scholar] [CrossRef] - Kirjanów, A.; Burduk, R. Regression method-based analysis of damage development in the core of steel cord conveyor belts. In Proceedings of the XVIII Conference of PhD Students and Young Scientists, Szklarska Poręba, Poland, 22–25 May 2018; p. 5. [Google Scholar]
- Kozłowski, T.; Błażej, R. 2018 Influence of selected parameters on the magnetic testing results in a DiagBelt system. Transp. Przemysłowy Masz. Rob.
**2018**, 4, 6–9. (In Polish) [Google Scholar] - Olchówka, D. Selection of Measurement Parameters Using the DiagBelt Magnetic System on the Test Conveyor. Master’s Thesis, Wroclaw University of Science and Technology, Wroclaw, Poland, 2020. (In Polish). [Google Scholar]
- Hazra, A. Using the confidence interval confidently. J. Thorac. Dis.
**2017**, 9, 4125–4130. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Olchówka, D.; Jurdziak, L.; Błażej, R.; Kozłowski, T. Examination of the steel cord belts core damage condition using the DiagBelt system Part 1. Determining the number of steel cord cuts in damage. Transp. Przemysłowy Masz. Rob.
**2021**, 1, 2–10. (In Polish) [Google Scholar] - Omran, M.; Engelbrecht, A.; Salman, A. An overview of clustering methods. Intell. Data Anal.
**2007**, 11, 583–605. [Google Scholar] [CrossRef] - Saxena, A.; Prasad, M.; Gupta, A.; Bharill, N.; Patel op Tiwari, A.; Er, M.; Lin, C. A Review of Clustering Techniques and Developments. Neurocomputing
**2017**, 267, 664–681. [Google Scholar] [CrossRef] [Green Version] - Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators. Neural Netw.
**1989**, 2, 359–366. [Google Scholar] [CrossRef] - Osowski, S. Neural Networks for Information Processing; Oficyna Wydawnicza Politechniki Warszawskiej: Warszawa, Poland, 2020. (In Polish) [Google Scholar]
- Phil, K. MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence; Apress: Berkeley, CA, USA, 2017. [Google Scholar]
- Anghel, D.; Ene, A.; Belu, N. A Matlab Neural Network Application for the Study of Working Conditions. Adv. Mater. Res.
**2013**, 837, 310–315. [Google Scholar] [CrossRef] - Demuth, H.; Beale, M. Neural Network Toolbox User’s Guide; MathWorks, Inc.: Portola Valley, CA, USA, 2014. [Google Scholar]
- Osowski, S. Neural Networks in Algorithmic Use; Wydawnictwo Naukowo Techniczne: Warszawa, Poland, 1996. (In Polish) [Google Scholar]
- Jurdziak, L.; Błażej, R.; Bajda, M. Conveyor belt 4.0, Intelligent systems in production engineering and maintenance. Adv. Intell. Syst. Comput.
**2019**, 835, 645–654. [Google Scholar] - Integrated Mobile System of Automatic Testing and Continuous Diagnostics of the Condition of Conveyor Belts. Available online: https://mapadotacji.gov.pl/projekty/1179135/ (accessed on 30 April 2021).

**Figure 2.**2D images of the damage for significantly different settings of measuring equipment parameters.

**Figure 6.**Inconclusive image of the damage for the measurement with high sensitivity of the measuring probe (scale 5 mm/pixel).

**Figure 8.**Confidence intervals test set, (

**a**)–Z1sum (overlapping intervals), (

**b**)–Nsum, (

**c**)–Z2sum, (

**d**)–N_LK (data outside of assigned value).

Belt Speed [m/s] | Range between the Belt Core and the Measuring Probe [mm] | Sensitivity [mV] |
---|---|---|

2 | 20–50 | 200–300 |

3 | 20–50 | 300–400 |

4 | 20–50 | 400–500 |

5 | 20–50 | 600–700 |

U1 | U2 | U3 | U4 | U5 | U6 | ||
---|---|---|---|---|---|---|---|

Z1sum | $\overline{x}$ | 0.00 | 3.09 | 45.72 | 373.48 | 793.65 | 130.91 |

$\Delta $ | 0.00 | 12.67 | 44.37 | 94.09 | 136.12 | 80.08 | |

Z1_LK | $\overline{x}$ | 0.00 | 0.09 | 0.79 | 3.40 | 5.17 | 1.61 |

$\Delta $ | 0.00 | 0.08 | 0.23 | 0.17 | 0.21 | 0.27 | |

Nsum | $\overline{x}$ | 20.50 | 110.20 | 231.10 | 542.26 | 821.79 | 334.82 |

$\Delta $ | 2.07 | 8.29 | 13.12 | 16.09 | 25.25 | 14.44 | |

N_LK | $\overline{x}$ | 0.88 | 2.29 | 3.68 | 6.01 | 8.04 | 4.46 |

$\Delta $ | 0.07 | 0.12 | 0.14 | 0.11 | 0.14 | 0.15 | |

Z2sum | $\overline{x}$ | 0.00 | 2.40 | 43.95 | 395.60 | 848.97 | 103.40 |

$\Delta $ | 0.00 | 3.83 | 14.06 | 32.92 | 45.95 | 21.77 | |

Z2_LK | $\overline{x}$ | 0.00 | 0.04 | 0.61 | 3.24 | 4.89 | 1.24 |

$\Delta $ | 0.00 | 0.05 | 0.18 | 0.19 | 0.18 | 0.23 |

U1 | U2 | U3 | U4 | U5 | U6 | |
---|---|---|---|---|---|---|

Z1sum | 0.00 | 1.03 | 45.79 | 377.27 | 788.06 | 131.00 |

Z1_LK | 0.00 | 0.06 | 0.75 | 3.40 | 5.17 | 1.63 |

Nsum | 20.75 | 107.94 | 230.48 | 538.98 | 815.54 | 332.23 |

N_LK | 1.00 | 2.26 | 3.67 | 6.04 | 8.04 | 4.46 |

Z2sum | 0.00 | 0.00 | 42.33 | 400.04 | 843.58 | 104.23 |

Z2_LK | 0.00 | 0.00 | 0.60 | 3.19 | 4.92 | 1.21 |

Variant | No | Recognition Effectiveness [%] | ||||||
---|---|---|---|---|---|---|---|---|

U1 | U2 | U3 | U4 | U5 | U6 | Total | ||

1 | 1 | 98.57 | 99.19 | 99.67 | 99.69 | 100.00 | 100.00 | 99.37 |

2 | 97.14 | 97.56 | 98.68 | 98.13 | 100.00 | 100.00 | 98.86 | |

3 | 100.00 | 98.37 | 98.03 | 98.13 | 100.00 | 100.00 | 98.99 | |

2 | 1 | 100.00 | 97.14 | 97.92 | 100.00 | 100.00 | 100.00 | 99.13 |

2 | 100.00 | 97.14 | 97.92 | 100.00 | 100.00 | 100.00 | 99.13 | |

3 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Olchówka, D.; Rzeszowska, A.; Jurdziak, L.; Błażej, R.
Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts. *Energies* **2021**, *14*, 3081.
https://doi.org/10.3390/en14113081

**AMA Style**

Olchówka D, Rzeszowska A, Jurdziak L, Błażej R.
Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts. *Energies*. 2021; 14(11):3081.
https://doi.org/10.3390/en14113081

**Chicago/Turabian Style**

Olchówka, Dominika, Aleksandra Rzeszowska, Leszek Jurdziak, and Ryszard Błażej.
2021. "Statistical Analysis and Neural Network in Detecting Steel Cord Failures in Conveyor Belts" *Energies* 14, no. 11: 3081.
https://doi.org/10.3390/en14113081