Artificial neural networks (ANNs) are designed and implemented to model the direct synthesis of dimethyl ether (DME) from syngas over a commercial catalyst system. The predictive power of the ANNs is assessed by comparison with the predictions of a lumped model parameterized to fit the same data used for ANN training. The ANN training converges much faster than the parameter estimation of the lumped model, and the predictions show a higher degree of accuracy under all conditions. Furthermore, the simulations show that the ANN predictions are also accurate even at some conditions beyond the validity range. 相似文献
During bio-oxidation of sulfides, the chemical state change of sulfur is a complex and key factor. It is not only an indicator of the extent and intensity of the bio-oxidation, but also controls the property of bio-leaching medium and the period of oxidation. The chemical state of sulfur in sulfides oxidized by leaching bacteria was studied with XPS. Sulfide minerals in the arsenic-bearing gold concentrate consist of pyrite, arsenopyrite, chalcopyrite, galena, sphalerite and so on. In order to probe the pattern of the chemical state change of sulfur in the bio-oxidation residue of arsenic-bearing gold concentrate, the structure of the grains, and the surface nature of the residue, XPS test was carried out through different sputtering duration. The study of XPS clearly shows that: sulfides is progressively oxidized from the surface of minerals to the core by leaching bacteria; the chemical valence of sulfur changes from S^2- or [S2]^2- to [SO4]^2- ; sulfur in the core is in a reduction state, S^2- or [S2]^2- , but exists in an oxidation state S^6 on the surface; due to the chemical state change of sulfur, mineral phase of the bio-oxidation residue is also changed(sulfides inside, while sulfates outside); the layered structure is found in the grains of the bio-oxidation residue. 相似文献
The useful life of a cutting tool and its operating conditions largely control the economics of the machining operations. Hence, it is imperative that the condition of the cutting tool, particularly some indication as to when it requires changing, to be monitored. The drilling operation is frequently used as a preliminary step for many operations like boring, reaming and tapping, however, the operation itself is complex and demanding.
Back propagation neural networks were used for detection of drill wear. The neural network consisted of three layers input, hidden and output. Drill size, feed, spindle speed, torque, machining time and thrust force are given as inputs to the ANN and the flank wear was estimated. Drilling experiments with 8 mm drill size were performed by changing the cutting speed and feed at two different levels. The number of neurons in the hidden layer were selected from 1, 2, 3, …, 20. The learning rate was selected as 0.01 and no smoothing factor was used. The estimated values of tool wear were obtained by statistical analysis and by various neural network structures. Comparative analysis has been done between statistical analysis, neural network structures and the actual values of tool wear obtained by experimentation. 相似文献