Machine Learning-Based Prediction of Specific Energy Consumption for Cut-Off Grinding.

Cut-off operation is widely used in the manufacturing industry and is highly energy-intensive. Prediction of specific energy consumption (SEC) using data-driven models is a promising means to understand, analyze and reduce energy consumption for cut-off grinding. The present article aims to put forth a novel methodology to predict and validate the specific energy consumption for cut-off grinding of oxygen-free copper (OFC-C10100) using supervised machine learning techniques. State-of-the-art experimental setup was designed to perform the abrasive cutting of the material at various cutting conditions. First, energy consumption values were predicted on the bases of input process parameters of feed rate, cutting thickness, and cutting tool type using the three supervised learning techniques of Gaussian process regression, regression trees, and artificial neural network (ANN). Among the three algorithms, Gaussian process regression performance was found to be superior, with minimum errors during validation and testing. The predicted values of energy consumption were then exploited to evaluate the specific energy consumption (SEC), which turned out to be highly accurate, with a correlation coefficient of 0.98. The relationship of the predicted specific energy consumption (SEC) with material removal rate agrees well with the relationship depicted in physical models, which further validates the accuracy of the prediction models.

Coupling Taguchi experimental designs with deep adaptive learning enhanced AI process models for experimental cost savings in manufacturing process development.

The Aluminum alloy AA7075 workpiece material is observed under dry finishing turning operation. This work is an investigation reporting promising potential of deep adaptive learning enhanced artificial intelligence process models for L18 (6133) Taguchi orthogonal array experiments and major cost saving potential in machining process optimization. Six different tool inserts are used as categorical parameter along with three continuous operational parameters i.e., depth of cut, feed rate and cutting speed to study the effect of these parameters on workpiece surface roughness and tool life. The data obtained from special L18 (6133) orthogonal array experimental design in dry finishing turning process is used to train AI models. Multi-layer perceptron based artificial neural networks (MLP-ANNs), support vector machines (SVMs) and decision trees are compared for better understanding ability of low resolution experimental design. The AI models can be used with low resolution experimental design to obtain causal relationships between input and output variables. The best performing operational input ranges are identified for output parameters. AI-response surfaces indicate different tool life behavior for alloy based coated tool inserts and non-alloy based coated tool inserts. The AI-Taguchi hybrid modelling and optimization technique helped in achieving 26% of experimental savings (obtaining causal relation with 26% less number of experiments) compared to conventional Taguchi design combined with two screened factors three levels full factorial experimentation.

Acetone-Gasoline Blend as an Alternative Fuel in SI Engines: A Novel Comparison of Performance, Emission, and Lube Oil Degradation.

The disproportionate use of petroleum products and stringent exhaust emissions has emphasized the need for alternative green fuels. Although several studies have been conducted to ascertain the performance of acetone-gasoline blends in spark-ignition (SI) engines, limited work has been done to determine the influence of fuel on lubricant oil deterioration. The current study fills the gap through lubricant oil testing by running the engine for 120 h on pure gasoline (G) and gasoline with 10% by volume acetone (A10). Compared to gasoline, A10 produced better results in 11.74 and 12.05% higher brake power (BP) and brake thermal efficiency (BTE), respectively, at a 6.72% lower brake-specific fuel consumption (BSFC). The blended fuel A10 produced 56.54, 33.67, and 50% lower CO, CO2, and HC emissions. However, gasoline remained competitive due to lower oil deterioration than A10. The flash-point and kinematic viscosity, compared to fresh oil, decreased by 19.63 and 27.43% for G and 15.73 and 20.57% for A10, respectively. Similarly, G and A10 showed a decrease in total base number (TBN) by 17.98 and 31.46%, respectively. However, A10 is more detrimental to lubricating oil due to a 12, 5, 15, and 30% increase in metallic particles like aluminum, chromium, copper, and iron, respectively, compared to fresh oil. Performance additives like calcium and phosphorous in lubricant oil for A10 decreased by 10.04 and 4.04% in comparison to gasoline, respectively. The concentration of zinc was found to be 18.78% higher in A10 when compared with gasoline. A higher proportion of water molecules and metal particles were found in lubricant oil for A10.

Performance Evaluation of Phenol-Resin-Based Adsorbents for Heat Transformation Applications.

Phenol resins (PRs) are considered as relatively inexpensive adsorbents synthesized from agricultural biomass via employing a variety of synthesized procedures. The performance of PR for heat transformation application is not widely investigated. In this regard, the present study aims to evaluate the four PR derivative/refrigerant pairs, namely (i) KOH6-PR/CO2, (ii) SAC-2/HFC, (iii) KOH4-PR/ethanol, and (iv) KOH6-PR/ethanol, for adsorption cooling and adsorption heating applications. Ideal cycle analyses and/or thermodynamic modelling approaches were utilized comprising governing heat and mass balance equations and adsorption equilibrium models. The performance of the AHP system is explored by means of specific cooling energy (SCE), specific heating energy (SHE), and coefficient of performance (COP), both for cooling and heating applications, respectively. It has been realized that KOH6-PR/ethanol could produce a maximum SCE of 1080 kJ/kg/cycle and SHE of 2141 kJ/kg/cycle at a regeneration temperature (Treg) and condenser temperature (Tcond) of 80 °C, and 10 °C, respectively, followed by KOH4-PR/ethanol, SAC-2/HFC-32, and KOH6-PR/CO2. The maximum COP values were estimated to be 1.78 for heating and 0.80 for cooling applications, respectively, at Treg = 80 °C and Tcond = 10 °C. In addition, the study reveals that, corresponding to increase/decrease in condenser/evaporator pressure, both SCE and SHE decrease/increase, respectively; however, this varies in magnitude due to adsorption equilibrium of the studied PR derivative/refrigerant pairs.

Experimental and Computational Study of Mechanical and Thermal Characteristics of h-BN and GNP Infused Polymer Composites for Elevated Temperature Applications.

Polymer-based nanocomposites are being considered as replacements for conventional materials in medium to high-temperature applications. This article aims to discover the synergistic effects of reinforcements on the developed polymer-based nanocomposite. An epoxy-based polymer composite was manufactured by reinforcing graphene nanoplatelets (GNP) and h-boron nitride (h-BN) nanofillers. The composites were prepared by varying the reinforcements with the step of 0.1 from 0.1 to 0.6%. Ultrasonication was carried out to ensure the homogenous dispersion of reinforcements. Mechanical, thermal, functional, and scanning electron microscopy (SEM) analysis was carried out on the novel manufactured composites. The evaluation revealed that the polymer composite with GNP 0.2 by wt % has shown an increase in load-bearing capacity by 265% and flexural strength by 165% compared with the pristine form, and the polymer composite with GNP and h-BN 0.6 by wt % showed an increase in load-bearing capacity by 219% and flexural strength by 114% when compared with the pristine form. Furthermore, the evaluation showed that the novel prepared nanocomposite reinforced with GNP and h-BN withstands a higher temperature, around 340 °C, which is validated by thermogravimetric analysis (TGA) trials. The numerical simulation model is implemented to gather the synthesised nanocomposite's best composition and mechanical properties. The minor error between the simulation and experimental data endorses the model's validity. To demonstrate the industrial applicability of the presented material, a case study is proposed to predict the temperature range for compressor blades of gas turbine engines containing nanocomposite material as the substrate and graphene/h-BN as reinforcement particles.