Failure load prediction and optimisation for adhesively bonded joints enabled by deep learning and fruit fly optimisation. (October 2022)

• Record Type: Journal Article
• Authors: Li, Weidong; Liang, Yuchen; Liu, Yiding
• Is Part Of: Advanced engineering informatics. Volume 54(2022)
• Publication Date: 2022-10
• Subjects: Adhesively bonded joint -- Deep neural network -- Transfer learning; E1 and E2 The upper and lower ranges of the elastic modulus of upper and lower adherends -- G1and G2 The upper and lower ranges of the fracture toughness of upper and lower adherends -- Loadf(Al, i) Joint failure load of aluminium materialSLJs -- Loadf(Compos, i) Joint failure load of composite SLJs -- ∅1 The load difference between experimental and FEA results -- ∅2 The difference of samples between two domains (i.e., the aluminium and composite SLJs) -- ∅3 The loss function -- ∅4 The loss function for DNN -- sup⁡(∙) The supremum of the aggregate -- H(∙) Reproducing Kernel Hilbert Space -- MMD Maximum Mean Discrepancy -- MSE Mean Squared Error -- ω1 and ω2 The weights for loss function -- flyi fruit fly -- LBi and UBi the lower and upper boundaries of the joint parameters for the fruit fly, respectively -- rand() Random value between 0 and 1 -- flycentre Swarm centre -- new_flyi New fruit fly -- α The search step -- c The value to determine whether the swarm centre with a worse joint failure load will be accepted or not -- I The current iteration -- Loadf(matl, i)_FEA The ground-truth value by the FEA model -- Loadf(matl, i)_DNN The predicted joint failure load by the DNN model for the ith dataset -- P The prediction performance -- TX The time complexity; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101817
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlight: A deep neural network enhanced by transfer learning is designed for joint failure load prediction. A fruit fly optimisation algorithm is developed to achieve the best joint parameters. Case studies are conducted to demonstrate the effectiveness of the approach. Abstract: Adhesively bonded joints have been extensively employed in the aeronautical and automotive industries to join thin-layer materials for developing lightweight components. To strengthen the structural integrity of joints, it is critical to estimate and improve joint failure loads effectually. To accomplish the aforementioned purpose, this paper presents a novel deep neural network (DNN) model-enabled approach, and a single lap joint (SLJ) design is used to support research development and validation. The approach is innovative in the following aspects: (i) the DNN model is reinforced with a transfer learning (TL) mechanism to realise an adaptive prediction on a new SLJ design, and the requirement to re-create new training samples and re-train the DNN model from scratch for the design can be alleviated; (ii) a fruit fly optimisation (FFO) algorithm featured with the parallel computing capability is incorporated into the approach to efficiently optimise joint parameters based on joint failure load predictions. Case studies were developed to validate the effectiveness of the approach. Experimental results demonstrate that, with this approach, the number of datasets and the computational time required to re-train the DNN model for a new SLJ design were significantly reduced by 92.00% and 99.57% respectively, and the joint failure load was substantially increased by 9.96%.