Simulation and Experimental Study of Inverse Heat Conduction Problem

Abstract

In this paper, a neural network method is proposed to solve a one dimensional inverse heat conduction problem (IHCP). The method relies on input/output data of an unknown system to create an intelligent neural network model. Multi layer perceptrons with recurrent properties are utilised in the model. Prepared input/output data are used to train the neural network. Reliable checking processes are also offered to justify the robustness of the method. A numerical sequential function specification (SFS) method is used as another technique to solve the IHCP. The numerical result is compared with that of the proposed method and good agreement is shown between the two methods. However, the numerical method can be only used to solve the IHCP off-line due to the high computation requirement. The proposed neural network method can be used in real-time situations as shown in the experimental tests.

Laboratory Experimental Setup and Research on Heat Transfer Characteristics during Secondary Cooling in Continuous Casting

“…Normally, it is difficult to measure surface heat flux and temperature of a slab undergoing air mist spray cooling. When thermocouples are set at a certain distance from the surface of the slab to measure temperatures at different positions, a mathematical model can be used to calculate the surface heat flux and surface temperature [15,16]. The heat boundary condition can be calculated by recording the temperature as a function of time, which is in the form of an inverse heat transfer problem [17].…”

An Artificial Intelligence Solution for Heat Flux Estimation Using Temperature History; A Two-Input/Two-Output Problem

“…AI techniques do not use thermal equations in their algorithms. AI has triggered innovations in inverse models for real-time heat flux estimation in thermal systems (Chen, et al, 2011), including complex irradiative models (Mirsepahi, et al, 2013). Two advantages of AI inverse models make them superior to optimisation-based heat flux estimation methods.…”