Yakub Mogul Dr

In this work, machine learning driven back propagation neural network framework has been developed to predict the surface roughness during abrasive water jet machining (AWJM) of Ti6Al4V. The experiments were performed as per the Taguchi based L27 orthogonal array, which generated the required dataset for developing the predictive model. A backpropagation neural network (BpNN) supported by a purpose-built graphical user interface (GUI) was used to formulate the data and allow multi-stage validation. To amplify the learning database, 50 synthetic datasets were produced and evaluated using K–fold Cross–Validation out of which, 70% of the data was used for training, 20% was used for testing, and 10% for validation. The 1–10–5 architecture achieved a high correlation coefficient (R) of 0.9728, with an average accuracy ranging between 90–95%. The model’s predictability was further verified through confirmatory experiments, yielding deviations of 0.12–7.09%. The findings confirmed that the proposed BpNN model effectively captured the non-linear relationships amongst the different process parameters used in this study. SEM analysis corroborated the predicted trends, showing smoother morphology at lower erosive energies and pronounced micro-ploughing, ridging, and brittle micro-chipping at higher parameter intensities. Sensitivity analysis revealed that water pressure and traverse speed were highly influential, contributing to about 36.7% and 29.7%, respectively, on surface roughness variability. Overall, the proposed BpNN-GUI technique provided a reliable foundation for digital-twin-based optimization of AWJM for difficult-to-cut titanium alloys.
[Display omitted]

Metamaterials are engineered materials with unique properties arising from their structure rather than composition, featuring repeating patterns smaller than the wavelengths they affect. Meta-biomaterials are an important subset of metamaterials and have drawn increasing interest in recent times due to their favorable mechanical properties, biological properties and functional integrity. These exceptional properties have enabled their suitability for diverse biomedical applications, including orthopedic/dental implants, tissue engineering, and medical devices. These materials are generally subjected to cyclic musculoskeletal loads after implantation, making the study of their fatigue behavior critical for ensuring long-term reliability. The current review, therefore, focuses on the fatigue behavior of meta-biomaterials that are manufactured using different additive manufacturing techniques. Various factors like topological design, base material/alloy selection, type of fatigue loading, manufacturing and secondary treatment processes, etc., are carefully analysed, and their influence on fatigue performance is studied. Furthermore, the failure mechanisms of additively manufactured meta-biomaterials with different geometries, structures, and architectures are also analyzed. Thus, this comprehensive review not only elucidates the underlying fatigue mechanisms, but also establishes a framework for the rational design of next-generation of biomedical implants with enhanced durability and functionality.

The current study focusses on developing a back propagation neural network model for depth of cut during the abrasive water jet machining of a Ti-6AL-4V aluminum alloy. The study analyzed depth of cut for five different water jet abrasive parameters namely, water pressure, transverse speed, abrasive mass flow rate, abrasive orifice size, and nozzle to orifice diameter. Experiments were conducted as per the L27 Taguchi-design of experiments (DoE). The back propagation neural network model comprising of one input layer, one hidden layer and an output layer with an architecture of 1–5–6 was chosen for conducting the analysis. The algorithm predicted the Taguchi based output values for the experimental depth of cut with an accuracy of up to 95 %. The neural network algorithm further automated itself, generating 50 new data sets for K-cross validation, out of which 70 %, 20 %, and 10 % of the data were used for training, testing, and validation, respectively. Confirmatory experiments were conducted for depth of cut and assessed against the data set used for validation (10 %). The results showed that as the depth of cut was small, i.e., ranging from 3 mm to 5 mm, the algorithm was unable to predict the optimized parameters, however, the prediction improved as the depth of cut increased. Overall, the consistency between the neural network predicted and the experimental depth of cut throughout the algorithm confirmed the validity of the procedure and the appropriateness of the algorithm.

This review presents design, analysis and experimental analysis of metamaterials with tunable properties for biomedical applications. Five different metamaterials namely, lightweight metamaterials, pattern transformation metamaterials, negative compressibility metamatrials, pentamode metamaterials and auxetic metamaterials have been discussed in detail with emphasis of these materials in the field of biomedicine. Furthermore, different addivitve manufacturing techniques implemented in the manufacturing of these biomaterials may be customized to provide different mechanical characteristics. Finally, the mechanical properties and deformation mechanisms for the biomaterials have been discussed.

The present work investigates the mechanical properties of a composite material composed of multi-walled carbon nanotubes (MWCNTs), nano-aluminum powder (NAP), and glass fibers (GF) for five different compositions. The study further investigated how MWCNTs contribute to maintaining the mechanical properties of nanocomposites when exposed to elevated temperatures, up to 180 °C. The evaluation of impact strength revealed that the nanocomposite, composed of 2 % MWCNTs, 15 % NAP, and 10 % GF, demonstrated the greatest impact strength. At room temperature, the composite containing 2 % MWCNTs, 5 % NAP, and 20 % GF exhibited the highest ultimate tensile strength (UTS). Conversely, at elevated temperatures reaching up to 180 °C, the highest UTS was observed in the composition with 2 % MWCNTs, 10 % NAP, and 15 % GF. The hardness of the nanocomposite was influenced by its composition; at room temperature, the maximum hardness was observed in the mixture containing 2 % MWCNTs, 20 % NAP, and 5 % GF. In contrast, at elevated temperatures, the composition with 2 % MWCNTs, 5 % NAP, and 20 % GF exhibited the highest hardness. Overall, the study found that incorporating GF and NAP improved the mechanical properties of the composite. These results indicate that the composite's performance could be further optimized for specific applications through the addition of filler materials.

Auxiliary systems, such as regeneration and intercooling, have been integrated with the primary gas generator to improve power production and fuel economy in modern gas turbine power plants. Implementing these techniques in turbine engines is challenging due to size, weight, and complex flow patterns. A solution is to use a turboprop engine with a smaller mass flow rate and simpler gas paths. The current study involves the numerical analysis of performance parameters namely, specific power (SP), thermal efficiency (eta), and enthalpy based specific fuel consumption (EBSFC) of a turboprop engine using thermodynamic parameters namely, pressure ratio (PR), nozzle pressure ratio (NPR), turbine inlet temperature (TIT), regeneration efficiency (R), and intercooling efficiency (E). The results prove that the introduction of regeneration and intercooling showed significant improvement in the power developed, and reduced fuel consumption.

Molten salts are highly effective as a quenching medium for austempering and martempering processes, enabling precise control of cooling rates to achieve the desired microstructures and mechanical characteristics in steel components. One such promising molten salt is a multicomponent Ca (NO3)2-KNO3 molten salt. The current work explores the cooling severity of molten Ca (NO3)2-KNO3 mixtures, which are commonly used for such purposes. The said mixture, with varying concentrations and bath temperatures was used for quenching the Inconel probe with thermocouples. The temperature data extracted was used to determine the transient heat flux developed at the metal?quenchant interface. A set of critical points were assessed against the peak heat extraction rates. Additionally, the fluctuation of mean heat flux and surface temperature in relation to these crucial points were plotted, along with changes in composition and bath temperature of the quench media. The cooling intensity of these quench solutions, as measured by Inconel probes, correlated well with the average hardness values observed in steel probes. The level of homogeneity in heat transmission, as measured by the spatial variance of the normalized heat energy, decreased as the percentage of KNO3 in the quench medium increased.

The bubble departure and lift-off boiling (BDL) model was studied using computational intelligence techniques and hybrid algorithms. Quite a few studies have predicted the relationship between wall heat fluxes and wall temperature in the form of flow boiling curves. The output wall temperature is a performance indicator that depends on many operating parameters. The current study, therefore, analyses the predictability of the wall temperature in terms of operating pressure, bulk flow velocity, and wall heat flux, based on the BDL model developed by Zenginer, which included two suppression factors namely, flow-induced and subcooling factors, respectively. The soft computing techniques used for prediction were - the artificial neural network (ANN), and the Fuzzy Mamdani model, and the hybrid algorithms were adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network trained particle swarm optimization (ANN-PSO). In addition, the ANN-PSO conducted a parametric analysis to evaluate the best model configuration by considering various factors. The comparison of all four techniques showed that the ANFIS model exhibited the prediction performance for wall temperature. Moreover, the results obtained from the ANFIS model have been compared with the different flow boiling curves from the literature and observed that the curve fitted well for higher bulk flow velocities with an MSE and R2 was found to be 0.85 % and 0.9933, respectively.

Multi-objective grey relational analysis optimization technique and multiple regression analysis were employed to determine the optimum values for depth of cut, surface roughness ( R
a
), and kerf at entry and exit ([Formula: see text] and [Formula: see text]), for abrasive waterjet machining of Ti6AL4V materials. This method highlights a new process to extend the grey relational analysis technique for determining the optimum conditions for obtaining the best quality characteristics. The input parameters of the study were water pressure ( W
p
), transverse speed ( T
s
), abrasive mass flow rate ( A
mf
), abrasive orifice size ( A
os
), nozzle/orifice diameter ratio ( N/O
dia
). The experiments were conducted as per the Taguchi-based L
27
orthogonal array. The grey relational analysis technique found that T
s
was the most significant parameter on the combined outputs. The regression models developed had an R
2
of 81.58%, 79.79%%, 77.20%, and 74.39% for depth of cut, R
a
, [Formula: see text] and [Formula: see text], respectively. Additionally, the analysis of variance showed that W
p
and A
os
had a significant influence on the output parameters. The predicted values were found to be reasonably close with the experimental values, and the maximum average deviation was 8.15% for [Formula: see text].

Using the data obtained from the computational fluid dynamics simulations, a back-propagation neural network model was developed to predict the velocity magnitudes and the instantaneous wall shear stresses in two patient-specific aneurysms. The models were also used to determine the effect of the blood composition on the rapture risk of the aneurysms. Based on the possible combination, five back propagation models were developed. The architecture of five models is determined based on number of neurons in the hidden layer. All the models in each algorithm were trained and tested. The accuracy of the developed models was evaluated through statistical analysis of the network output in terms of mean absolute error, root mean squared error, mean squared error, and error deviation. According to the results obtained, all BPA effectively predicted velocity magnitude and instantaneous wall shear stress. Model 1 was, however, less accurate when compared to the other five models, as it had one neuron in its hidden layer. The analysis confirms that the neuron number in the hidden layer play a definitive role in predicting the respective outputs. The performance assessment all of the back-propagation models revealed that the error incurred was acceptable. The algorithms' training and testing in this study were satisfactory, since the network output was in reasonably good conformity with the target computational fluid dynamics result.