Modeling and Multiresponse Optimization of the Mechanical Properties of Roselle Fiber-Reinforced Vinyl Ester Composite

In this study, the roselle fiber-reinforced vinyl ester composites were prepared based on Taguchi’s L₂₇ experimental design using hand lay-up technique. A gray-based Taguchi technique was used to optimize the process parameters with mechanical properties (multiple performance characteristics). The results also show that the fiber content is the most significant process parameter which greatly affects the mechanical properties. It was proved that the multiple performance characteristics of the plant-based natural fiber-reinforced polymer composites can be effectively improved by this method. The proposed response surface mathematical models to predict mechanical properties of composite were found statistically valid.     

Tensile properties of modified 9Cr-1Mo steel by shear punch testing and correlation with microstructures

Modified 9Cr-1Mo ferritic steel (P91) is subjected to a series of heat treatments consisting of soaking for 5 min at the selected temperatures in the range 973 K–1623 K (below Ac₁ to above Ac₄) followed by oil quenching and tempering at 1033 K for 1 h to obtain different microstructural conditions. The tensile properties of the different microstructural conditions are evaluated from small volumes of material by shear punch test technique. A new methodology for evaluating yield strength, ultimate tensile strength and strain hardening exponent from shear punch test by using correlation equations without employing empirical constants is presented and validated. The changes in the tensile properties are related to the microstructural changes of the steel investigated by electron microscopic studies. The steel exhibits minimum strength and hardness when soaked between Ac₁ and Ac₃ (intercritical range) temperatures due to the replacement of original lath martensitic structure with subgrains. The finer martensitic microstructure produced in the steel after soaking at temperatures above Ac₃ leads to a monotonic increase in hardness and strength with decreasing strain hardening exponent. For soaking temperatures above Ac₄, the hardness and strength of the steel increases marginally due to the formation of soft δ ferrite.     

Cloud vendor selection for the healthcare industry using a big data-driven decision model with probabilistic linguistic information

Applied Intelligence - The role of cloud services in the data-intensive industry is indispensable. Cision recently reported that the cloud market would grow to 55 billion USD, with an active...     

Dark fermentative biohydrogen production by Acinetobacter junii-AH4 utilizing various industry wastewaters

Hydrogen (H₂) is one of the most promising renewable energy sources, anaerobic bacterial H₂ fermentation is considered as one of the most environmentally sustainable alternatives to meet the potential fossil fuel demand. Bio-H₂ is the cleanest and most effective source of energy provided by the dark fermentation utilizing organic substrates and different wastewaters. In this study, the bio-H₂ production was achieved by using the bacteria Acinetobacter junii-AH4. Further, optimization was carried out at different pH (5.0–8.0) in the presence of wastewaters as substrates (Rice mill wastewater (RMWW), Food wastewater (FWW) and Sugar wastewater (SWW). In this way, the optimized experiments excelled with the maximum cumulative H₂ production of 566.44 ± 3.5 mL/L (100% FWW at pH 7.5) in the presence of Acinetobacter junii-AH4. To achieve this, a bioreactor (3 L) was employed for the effective production of H₂ and Acinetobacter junii-AH4 has shown the highest cumulative H₂ of 613.2 ± 3.0 mL/L, HPR of 8.5 ± 0.4 mL/L/h, HY of 1.8 ± 0.09 mol H₂/mol glucose. Altogether, the present study showed a COD removal efficiency of 79.9 ± 3.5% by utilizing 100% food wastewater at pH 7.5. The modeled data established a batch fermentation system for sustainable H₂ production. This study has aided to achieve an ecofriendly approach using specific wastewaters for the production of bio-H₂.     

Interfacial and Bulk Magnetic Properties of Stoichiometric Cerium Doped Terbium Iron Garnet Polycrystalline Thin Films

One of the best magneto‐optical claddings for optical isolators in photonic integrated circuits is sputter deposited cerium‐doped terbium iron garnet (Ce:TbIG) which has a large Faraday rotation (≈?3500° cm^?1 at 1550 nm). Near‐ideal stoichiometry $\left(\frac{\text{Ce}+\text{Tb}}{\text{Fe}}=0.57\right)$ of Ce_0.5Tb_2.5Fe_4.75O₁₂ is found to have a 44 nm magnetic dead layer that can impede the interaction of propagating modes with garnet claddings. The effective anisotropy of Ce:TbIG on Si is also important, but calculations using bulk thermal mismatch overestimate the effective anisotropy. Here, X‐ray diffraction measurements yield highly accurate measurements of strain that show anisotropy favors an in‐plane magnetization in agreement with the positive magnetostriction of Ce:TbIG. Upon doping TbIG with Ce, a slight decrease in compensation temperature occurs which points to preferential rare‐earth occupation in dodecahedral sites and an absence of cation redistribution between different lattice sites. The high Faraday rotation, large remanent ratio, large coercivity, and preferential in‐plane magnetization enable Ce:TbIG to be an in‐plane latched garnet, immune to stray fields with magnetization collinear to direction of light propagation.     

Big data driven jobs remaining time prediction in discrete manufacturing system: a deep learning-based approach

Implementing advanced big data (BD) analytic is significant for successful incorporation of artificial intelligence in manufacturing. With the widespread deployment of smart sensors and internet of things (IOT) in the job shop, there is an increasing need for handling manufacturing BD for predictive manufacturing. In this study, we conceive the jobs remaining time (JRT) prediction during manufacturing execution based on deep learning (DL) with production BD. We developed a procedure for JRT prediction that includes three parts: raw data collection, candidate dataset design and predictive modelling. First, the historical production data are collected by the widely deployed IOT in the job shop. Then, the candidate dataset is formalised to capture various contributory factors for JRT prediction. Further, a DL model named stacked sparse autoencoder (S-SAE) is constructed to learn representative features from high dimensional manufacturing BD to make robust and accurate JRT prediction. Our work represents the first DL model for the JRT prediction at run time during production. The proposed methods are applied in a large-scale job shop that is equipped with 44 machine tools and produces 13 types of parts. Lastly, the experimental results show the S-SAE model has higher accuracy than previous linear regression, back-propagation network, multi-layer network and deep belief network in JRT prediction.     

Processing of Thermoplastic Composites Using a Powder Slurry Technique. I. Impregnation and Preheating

The success of thermoplastic matrix composites depends upon the development of economical methods of impregnation. The purpose of this work was to develop and understand an economical impregnation procedure using a slurry based powder technology. An impregnation and preheating line consisting of a fiber tensioner, a slurry bath, a drying heater, a coating heater, and a fiber winder was used to make resin coated fibers. The influence of the process parameters on the impregnation, preheating, coating, and consolidation were studied. Part I of this paper presents the experimental investigation of the impregnation and preheating stages of the process together with a preheating model. Luikov's coupled equations of heat and mass transfer were used to model the heating and drying of the tow in the preheater. The predictions of the preheating and drying model are compared to the experimentally obtained results.     

An integrated inventory optimization model for facility location-allocation problem

This paper presents an integrated inventory distribution optimisation model for multiple products in a multi-echelon supply chain environment. Inventory, transportation and location decisions are considered. The objective is to offer practical guideline to the steel retail supply chain practitioners in choosing the correct distribution centre, finding out inventory level at individual inventory keeping points (retailers and distribution centres) point thereby helping them in reducing overall distribution cost. The framework presented endorses systems approach and suggests near-optimal approach to calculating inventory for an individual distributor and his retailers. Two algorithms are used to solve this problem, a novel hybrid Multi-objective Self-learning particle swarm optimiser and Non-dominated sorting genetic algorithm-II. The model and solution methods are tested on real data-sets obtained from organisations in the steel retail environment. The actual data on inventory holding, ordering and transportation costs of distributors and retailers are used as inputs. The decisions like choosing correct set of Distribution centres, keeping optimal regular and safety stock inventory levels are arrived at by applying practical constraints in the supply chain. Model developed assists in effective and efficient distribution of the products manufactured from the optimal location at minimal cost.     

Automated Deep Learning Based Cardiovascular Disease Diagnosis Using ECG Signals

Automated biomedical signal processing becomes an essential process to determine the indicators of diseased states. At the same time, latest developments of artificial intelligence (AI) techniques have the ability to manage and analyzing massive amounts of biomedical datasets results in clinical decisions and real time applications. They can be employed for medical imaging; however, the 1D biomedical signal recognition process is still needing to be improved. Electrocardiogram (ECG) is one of the widely used 1-dimensional biomedical signals, which is used to diagnose cardiovascular diseases. Computer assisted diagnostic models find it difficult to automatically classify the 1D ECG signals owing to time-varying dynamics and diverse profiles of ECG signals. To resolve these issues, this study designs automated deep learning based 1D biomedical ECG signal recognition for cardiovascular disease diagnosis (DLECG-CVD) model. The DLECG-CVD model involves different stages of operations such as pre-processing, feature extraction, hyperparameter tuning, and classification. At the initial stage, data pre-processing takes place to convert the ECG report to valuable data and transform it into a compatible format for further processing. In addition, deep belief network (DBN) model is applied to derive a set of feature vectors. Besides, improved swallow swarm optimization (ISSO) algorithm is used for the hyperparameter tuning of the DBN model. Lastly, extreme gradient boosting (XGBoost) classifier is employed to allocate proper class labels to the test ECG signals. In order to verify the improved diagnostic performance of the DLECG-CVD model, a set of simulations is carried out on the benchmark PTB-XL dataset. A detailed comparative study highlighted the betterment of the DLECG-CVD model interms of accuracy, sensitivity, specificity, kappa, Mathew correlation coefficient, and Hamming loss.