The connections made between two substrates by an adhesive layer are used normally in many consumptions. The efficiency of the connections from these adhesives is evaluated normally by common traditional experimental, analytical, or numerical methods. Due to the absence of valid conventional methods to present a certain phenomenon correctly, machine learning methods can be used to release the data-driven models [11,12]. In recent studies, artificial intelligent methods were used to replace the traditional methods to analyze the glue line bonding strength of the wood-based composites to make the predictive models [11,13]. These methods can help decrease the large number of experiments to achieve the optimal solution and decrease the cost. The artificial neural network (ANN) is a famous artificial intelligence method that can be used to model the complex relationship between the variables [11]. ANNs have become increasingly popular due to their ability to solve complex problems in different contexts. This technique can draw the complex relation between the variables related to each other without any presumption [14]. ANNs are suitable in cases with numerous variables and complex relationships whose definition is difficult with mathematical equations. When ANNs are trained correctly, they can quickly conclude from a data input and consequently offer acceptable solutions on the problem. It has made the ANN method superior to many modeling approaches, such as the analytical and numerical methods. The most attractive advantage of ANN is the capability of modeling multi-dimensional nonlinear and complex formulae without considering the relationship behavior [15,16]. These methods support the understanding of very uncertain designs helping predict their future outcomes by producing a stable mechanism in materials science research so that the modeling of processes, optimization, and regression can be used in different sections, including the materials structure [17,18].
Numerical Methods Balaji Pdf Free Download
2ff7e9595c
Comments