[{“box”:0,”content”:”[if 992 equals=”Open Access”]n
n
Open Access
nn
n
n[/if 992]n
n
n
n
n
n
Gourav Vivek Kulkarni, Ramesh S Sharma, M.N. Vijaya Kumar, Sunith Babu L.,
n
- n t
n
n
n[/foreach]
n
n[if 2099 not_equal=”Yes”]n
- [foreach 286] [if 1175 not_equal=””]n t
- Student, Professor, Associate Professor, Associate Professor Department of Mechanical Engineering, RV College of Engineering, Bengaluru, Department of Mechanical Engineering, RV College of Engineering, Bengaluru, Department of Industrial Engineering and Management, RV College of Engineering, Bengaluru, Department of Mechanical Engineering, Ramaiah Institute of Technology, Bengalur, Karnataka, Karnataka, Karnataka, Karanataka India, India, India, India
n[/if 1175][/foreach]
n[/if 2099][if 2099 equals=”Yes”][/if 2099]n
Abstract
nRecent technological advancements, particularly the integration of neural networks, have facilitated a predictive approach to complex engineering problems, especially those involving composite materials with directional properties. The scarcity of literature on predicting impact damage using experimental and ultrasonic flaw detection data motivated this study. Experimental assessment of impact damage on carbon fiber/epoxy (CFRP) and glass fiber/epoxy (GFRP) composites was conducted using low-velocity drop weight impact testing. Damage assessment employed an ultrasonic flaw detector with a single crystal wedge delay probe, capturing damaged data in A-scan format. Load vs. time data from impact testing and point-wise damage detection data from ultrasonic testing were used to develop a Feedforward artificial neural network (ANN) with two hidden layers (64 neurons each) and a one-neuron output layer. Training epochs ranged from 100 to 1000, resulting in a decreasing trend of mean absolute error (MAE) over time. The ANN model demonstrated consistent accuracy in predicting impact damage thickness and loads for both CFRP and GFRP. This predictive capability holds promise for anticipating potential failures in composite structures under impact loads, enabling preventive design measures and enhancing structural reliability. The model’s versatility extends to incorporating C-Scan ultrasonic data, enhancing its utility in damage forecasting and mitigation strategies.
n
Keywords: Impact, damage, ultrasonic, ANN, prediction
n[if 424 equals=”Regular Issue”][This article belongs to International Journal of Fracture Mechanics and Damage Science(ijfmds)]
n
n
n
n
n
nn[if 992 equals=”Open Access”] Full Text PDF Download[/if 992] n
nn[if 379 not_equal=””]n
Browse Figures
n
n[/if 379]n
References
n[if 1104 equals=””]n
- Ge X, Zhang P, Zhao F, Liu M, Liu J, Cheng Experimental and numerical investigations on the dynamic response of woven carbon fibre reinforced thick composite laminates under low-velocity impact. Compos Struct. 2022; 279: 114792–114809.
- Sommer DE, Thomson D, Falcó O, Quino G, Cui H, Petrinic Damage modelling of carbon fibre composite crush tubes: Numerical simulation and experimental validation of drop weight impact. Compos Part A: Appl Sci Manuf. 2022; 160: 107033–107050.
- Andrew JJ, Srinivasan SM, Arockiarajan A, Dhakal H Parameters influencing the impact response of fibre-reinforced polymer matrix composite materials: A critical review. Compos Struct. 2019; 224: 111007–111033.
- Chen D, Luo Q, Meng M, Li Q, Sun Low velocity impact behavior of interlayer hybrid composite laminates with carbon/glass/basalt fibres. Compos B: Eng. 2019; 176: 107191–107203.
- Habibi M, Selmi S, Laperrière L, Mahi H, Kelouwani Post-impact compression behavior of natural flax fibre composites. J Nat Fibres. 2020; 17(11): 1683–1691.
- Cao S, Li HN, Huang W, Zhou Q, Lei T, Wu A delamination prediction model in ultrasonic vibration assisted drilling of CFRP composites. J Mater Process Technol. 2022; 302: 117480–117497.
- Tabatabaeian A, Jerkovic B, Harrison P, Marchiori E, Fotouhi Barely visible impact damage detection in composite structures using deep learning networks with varying complexities. Compos B: Eng. 2023; 264: 110907–110922.
- Mojtahedi A, Hokmabady H, Kouhi M, Mohammadyzadeh A novel ANN-RDT approach for damage detection of a composite panel employing contact and non-contact measuring data. Compos Struct. 2022; 279: 114794–114809.
- Qing X, Liao Y, Wang Y, Chen B, Zhang F, Wang Y. Machine learning based quantitative damage monitoring of composite structure. Int J Smart Nano Mater. 2022; 13(2): 167–
- Imoisili PE, Adeleke O, Makhatha ME, Jen T Response surface methodology (RSM)-artificial neural networks (ANN) aided prediction of the impact strength of natural fibre/carbon nanotubes hybrid reinforced polymer nanocomposite. Eng Sci. 2023; 23(852): 852–869.
- Zara A, Belaidi I, Khatir S, Brahim AO, Boutchicha D, Wahab M Damage detection in GFRP composite structures by improved artificial neural network using new optimization techniques. Compos Struct. 2023; 305: 116475–116495.
- Zhang K, Ma LH, Song ZZ, Gao H, Zhou W, Liu J, Tao Strength prediction and progressive damage analysis of carbon fibre reinforced polymer-laminate with circular holes by an efficient Artificial Neural Network. Compos Struct. 2022; 296: 115835–115847.
- Stephen C, Thekkuden DT, Mourad AHI, Shivamurthy B, Selvam R, Behara S Prediction of impact performance of fibre reinforced polymer composites using finite element analysis and artificial neural network. J Braz Soc Mech Sci Eng. 2022; 44(9): 408–419.
- Humer C, Höll S, Kralovec C, Schagerl Damage identification using wave damage interaction coefficients predicted by deep neural networks. Ultrasonics. 2022; 124: 106743–106762.
- Cheng X, Ma G, Wu Z, Zu H, Hu Automatic defect depth estimation for ultrasonic testing in carbon fibre reinforced composites using deep learning. NDT E Int. 2023; 135: 102804–102813.
- Babu LS, Kumar KA, Christiyan KJ, Byary MA, Puranic VM, Jawad AM, Poojary Effect of laminate thickness on low-velocity impact of GFRP/epoxy composites. Mater Today: Proc. 2023. (Article in press).
- Avinash SH, Singh NG, Makarand Damage detection methodology using ultrasonic non-destructive testing for composites structures. In Proceedings of the National Seminar & Exhibition on Non-Destructive Evaluation (NDE 2011), Chennai, India. 2011; 8–10.
- Arunprasath K, Naresh K, Amuthakkannan P, Manikandan V, Kavitha Study of low velocity impact failure responses of woven basalt fibre reinforced polymer composites using ultrasonic A, B and C scan techniques. Adv Mater Process Technol. 2023; 9(3): 1356–1379.
- Papa I, Lopresto V, Langella Ultrasonic inspection of composites materials: Application to detect impact damage. Int J Lightweight Mater Manuf. 2021; 4(1): 37–42.
- Alizadeh S, Ta S, Samavedham L, Ray A Application of artificial neural network for prediction of 10 crude oil properties. Can J Chem Eng. 2023; 101(11): 6203–6214.
- Le TT, Phan HC, Duong HT, Le M Optimal design of circular concrete-filled steel tubular columns based on a combination of artificial neural network, balancing composite motion algorithm and a large experimental database. Expert Syst Appl. 2023; 223: 119940–119968.
- Zatar W, Nghiem H, Chen G, Xiao Ultrasonic Pulse Echo Signals for Detection and Advanced Assessment of Reinforced Concrete Anomalies. Appl. Sci. 2024, 14, 4860. . doi: 10.20944/preprints202403. 1428.v1
nn[/if 1104][if 1104 not_equal=””]n
- [foreach 1102]n t
- [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]
n[/foreach]
n[/if 1104]
nn
nn[if 1114 equals=”Yes”]n
n[/if 1114]
n
n
n
International Journal of Fracture Mechanics and Damage Science
n
n
n
n
n
n
| Volume | 02 | |
| [if 424 equals=”Regular Issue”]Issue[/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] | 01 | |
| Received | June 20, 2024 | |
| Accepted | June 25, 2024 | |
| Published | August 9, 2024 |
n
n
n
n
n
n nfunction myFunction2() {nvar x = document.getElementById(“browsefigure”);nif (x.style.display === “block”) {nx.style.display = “none”;n}nelse { x.style.display = “Block”; }n}ndocument.querySelector(“.prevBtn”).addEventListener(“click”, () => {nchangeSlides(-1);n});ndocument.querySelector(“.nextBtn”).addEventListener(“click”, () => {nchangeSlides(1);n});nvar slideIndex = 1;nshowSlides(slideIndex);nfunction changeSlides(n) {nshowSlides((slideIndex += n));n}nfunction currentSlide(n) {nshowSlides((slideIndex = n));n}nfunction showSlides(n) {nvar i;nvar slides = document.getElementsByClassName(“Slide”);nvar dots = document.getElementsByClassName(“Navdot”);nif (n > slides.length) { slideIndex = 1; }nif (n (item.style.display = “none”));nArray.from(dots).forEach(nitem => (item.className = item.className.replace(” selected”, “”))n);nslides[slideIndex – 1].style.display = “block”;ndots[slideIndex – 1].className += ” selected”;n}n”}]