Utilization of adaptive neuro-fuzzy interference system and functional network in prediction of total organic carbon content

This paper presents the application of two artificial intelligence (AI) approaches in the prediction of total organic carbon content (TOC) in Devonian Duvernay shale. To develop and test the models, around 1250 data points from three wells were used. Each point comprises TOC value with corresponding spectral and conventional well logs. The tested AI techniques are adaptive neuro-fuzzy interference system (ANFIS) and functional network (FN) which their predictions are compared to existing empirical correlations. Out of these two methods, ANFIS yielded the best outcomes with 0.98, 0.90, and 0.95 correlation coefficients (R) in training, testing, and validation respectively, and the average errors ranged between 7 and 18%. In contrast, the empirical correlations resulted in R values less than 0.85 and average errors greater than 20%. Out of eight inputs, gamma ray was found to have the most significant impact on TOC prediction. In comparison to the experimental procedures, AI-based models produces continuous TOC profiles with good prediction accuracy. The intelligent models are developed from preexisting data which saves time and costs. Article highlights In contrast to existing empirical correlation, the AI-based models yielded more accurate TOC predictions. Out of the two AI methods used in this article, ANFIS generated the best estimations in all datasets that have been tested. The reported outcomes show the reliability of the presented models to determine TOC for Devonian shale.

Can wood-decaying urban macrofungi be identified by using fuzzy interference system? An example in Central European Ganoderma species

Ganoderma is a cosmopolitan genus of wood-decaying basidiomycetous macrofungi that can rot the roots and/or lower trunk. Among the standing trees, their presence often indicates that a hazard assessment may be necessary. These bracket fungi are commonly known for the crust-like upper surfaces of their basidiocarps and formation of white rot. Six species occur in central European urban habitats. Several of them, such as Ganoderma adspersum, G. applanatum, G. resinaceum and G. pfeifferi, are most hazardous fungi causing extensive horizontal stem decay in urban trees. Therefore, their early identification is crucial for correct management of trees. In this paper, a fast technique is tested for the determination of phytopathologically important urban macrofungi using fuzzy interference system of Sugeno type based on 13 selected traits of 72 basidiocarps of six Ganoderma species and compared to the ITS sequence based determination. Basidiocarps features were processed for the following situations: At first, the FIS of Sugeno 2 type (without basidiospore sizes) was used and 57 Ganoderma basidiocarps (79.17%) were correctly determined. Determination success increased to 96.61% after selecting basidiocarps with critical values (15 basidiocarps). These undeterminable basidiocarps must be analyzed by molecular methods. In a case, that basidiospore sizes of some basidiocarps were known, a combination of Sugeno 1 (31 basidiocarps with known basidiospore size) and Sugeno 2 (41 basidiocarps with unknown basidiospore size) was used. 84.72% of Ganoderma basidiocarps were correctly identified. Determination success increased to 96.83% after selecting basidiocarps with critical values (11 basidiocarps).

Slant type taper profiling and prediction of profiling speed for a circular profile during in wire electric discharge machining using Hastelloy-X

Hastelloy-X a nickel-based alloy used in nozzles, flame holders, turbine blades, turbocharges, jet engine tailpipes, afterburner components etc. having complex tapering profiles. Wire electric discharge machining proves to be the most beneficial machining technique as it provides required accuracy for the components. In the present research, a slant type taper fixture is employed for achieving taper angles as convention tapering have many hindrances like wire bend, angular inaccuracy, guide wear, insufficient flushing and wire breakage etc. and machining a simple circular profile on Hastelloy-X. The behaviour of different output parameters like profiling speed, surface roughness, profile areas, microhardness and recast layer were investigated for various input parameters for machined taper components at 0°, 15° and 30°. The cutting speed override parameter influenced most on the profiling speed and surface roughness. The wire offset parameter was found to be the most significant factor in the case of circular profile areas that were machined. The variation of different output parameters to profiling/cutting speed and taper angle was also highlighted. It is found the recast layer decreased which indicated lesser thermal degradation at higher taper angles at different profiling parameters. This is also validated by the microhardness where the machined surface hardness of taper angular profiles was found to be greater than the 0° profiles. The artificial neural networks and adaptive neuro-fuzzy interference system were used for the prediction of profiling speed. The adaptive neuro-fuzzy interference system was found better in prediction as the percentage error varies between 0–5 per cent. In conclusion, the profiling speed influences both on the accuracy and surface of machined taper circular profiles.