Prediction performance of PEM fuel cells by gene expression programming

Application of multi-gene genetic programming based on separable functional network for landslide displacement prediction

“…The fitness function of MGGP is an error minimization problem. Then, parameters about MGGP are chosen by two ways, one way is that to use training group and validate group to decide and the other way is chosen on the basis of some suggested values [27][28][29][30][31][32][33][34][35][36][37][38][39][40], which are given in Table 3 …”

“…In the recent past, GP and its variants such as parisian genetic programming (PGP) [26,27], gene expression programming (GEP) [28], cartesian genetic programming (CGP) [29,30] and MGGP [31][32][33] have been successfully applied to various kinds of problems [34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50]. Garg A et al [46][47][48][49][50] proposed several proved GP with machine learning can be applied into practical problems.…”

Development and validation of a GEP model to predict the performance and exhaust emission parameters of a CRDI assisted single cylinder diesel engine coupled with EGR

“…Such explicit correlation in terms of common mathematical operators provide a distinct advantage of a greater transparency and simplicity in interpreting the results and provide a scope of investigating and corroborating the credibility of the developed model through parametric sensitivity analyses. The potential advantages of a GEP based modelling strategy has already been explored and credited in various engineering problems [35,36,[40][41][42][43]. However, the footprint of GEP application in IC engine domains is yet to mature as is evident from the very sparse literature available [42,44].…”

“…Furthermore, in contrast to ANN, the evolved model responses, are explicit analytical functions of simple mathematical operators conducive to easier interpretation of the problem under study and obviate the need to comprehend the complexities of weight matrices in ANN endeavours. Compared to polynomial regression techniques, GEP strategy provides a superior alternative as it precludes the need to conform to predefined fitness functions [35][36][37]. Given sufficient experimental data during training, GEP has been observed to have the potential in adapting to complex, multidimensional and non-linear relationships accurately [38].…”

A new predictive model for the bond strength of FRP‐to‐concrete composite joints

“…Previous work has successfully used GP to model different variables in the field of material and chemical engineering such as calculating the hardness of metal matrix nanocomposites produced by mechanical alloying [11], minimizing the synthesis time of nanopowders in high energy ball milling [12], Charpy impact behaviour of Al6061/SiCp laminated nanocomposites [13], and performance of PEM fuel cells [14].…”