Effect of addition of recast materials on characteristics of Ni-Cr-Mo alloys

Comparative in-vitro microscopic evaluation of vertical marginal discrepancy, microhardness, and surface roughness of nickel-chromium in new and recast alloy

Reusing of alloy has become a need of time due to the increasing demand, depletion of resources, and substantial increase in their price. The alloys used require a long-term stay in the oral cavity exposed to a wet environment, so they must have good wear resistance, biocompatibility, and mechanically good strength. In this study, the vertical marginal discrepancy, surface roughness, and microhardness of the new and recast nickel-chromium (base metal) alloys were evaluated. 125 wax patterns were fabricated from a customized stainless steel master die with a heavy chamfer cervical margin divided into 5 groups. Each group had 25 samples. Group A: 25 wax patterns were cast using 100% by weight of new alloy, Group B: the casting was done by using 75% new alloy and 25% alloy by weight, Group C: wax patterns were cast using 50% new alloy and 50% alloy, Group D: 25% new alloy and 75% alloy and Group E: 100% recast alloy. The vertical marginal discrepancy was measured by an analytical scanning microscope, microhardness was tested on a universal testing machine, and surface roughness was on a tester of surface roughness. Castings produced using new alloys were better than those obtained with reused alloys. Alloys can be reused till 50% by weight along with the new alloy and accelerated casting technique can be used to save the lab time to fabricate castings with acceptable vertical marginal discrepancy, microhardness, and surface roughness. This indicated that 50% recasting of (Ni-Cr) can be used as a good alternative for the new alloy from an economical point of view.

The Use of Neural Networks and Genetic Algorithms to Control Low Rigidity Shafts Machining

The article presents an original machine-learning-based automated approach for controlling the process of machining of low-rigidity shafts using artificial intelligence methods. Three models of hybrid controllers based on different types of neural networks and genetic algorithms were developed. In this study, an objective function optimized by a genetic algorithm was replaced with a neural network trained on real-life data. The task of the genetic algorithm is to select the optimal values of the input parameters of a neural network to ensure minimum deviation. Both input vector values and the neural network’s output values are real numbers, which means the problem under consideration is regressive. The performance of three types of neural networks was analyzed: a classic multilayer perceptron network, a nonlinear autoregressive network with exogenous input (NARX) prediction network, and a deep recurrent long short-term memory (LSTM) network. Algorithmic machine learning methods were used to achieve a high level of automation of the control process. By training the network on data from real measurements, we were able to control the reliability of the turning process, taking into account many factors that are usually overlooked during mathematical modelling. Positive results of the experiments confirm the effectiveness of the proposed method for controlling low-rigidity shaft turning.