Optimization free neural network approach for solving ordinary and partial differential equations

Current work introduces a fast converging neural network-based approach for solution of ordinary and partial differential equations. Proposed technique eliminates the need of time-consuming optimization procedure for training of neural network. Rather, it uses the extreme learning machine algorithm for calculating the neural network parameters so as to make it satisfy the differential equation and associated boundary conditions. Various ordinary and partial differential equations are treated using this technique, and accuracy and convergence aspects of the procedure are discussed.

     

Atomic order-disorder engineering in the La2Zr2O7 pyrochlore under low energy ion irradiation

Cation and anion disordering affect the structural and electronic properties of the isometric A₂B₂O₇ pyrochlore materials. Here, we report a study on the structural response of La₂Zr₂O₇ at two different temperatures (300 K and ~88 K) as a function of ion fluence (1 × 10¹³, 5 × 10¹³, and 1 × 10¹⁴ ions/cm²). The effect of ion fluence and irradiation temperature on the structural properties have been investigated using the grazing angle x-ray diffraction, Raman spectroscopy, and high-resolution transmission electron microscopy. GIXRD results confirmed that the weakening/broadening of the diffraction peaks and lattice volume expansion increases monotonically as a function of ion fluence at both the temperatures and are more pronounced at ~88 K. The cation and anion disordering appear to be ion fluence and irradiation temperature-dependent. Raman spectroscopy shows that the atomic disordering is more pronounced with enhanced ion fluence and revealed the involvement of the X_48f parameter in the enhancement of disordering in the system. The HRTEM analysis revealed that the deterioration in the atomic ordering (amorphization) is significantly more pronounced at ~88 K. The qualitative analysis of cation/anion disordering and structural deformation revealed that irradiation parameters play a crucial role in developing and altering the properties of the pyrochlore materials for the technological applications.     

An expert system for process planning of sheet metal parts produced on compound die for use in stamping industries

Process planning of sheet metal part is an important activity in the design of compound die. Traditional methods of carrying out this task are manual, tedious, time-consuming, error-prone and experience-based. This paper describes the research work involved in the development of an expert system for process planning of sheet metal parts produced on compound die. The proposed system is organized in six modules. For development of system modules, domain knowledge acquired from various sources of knowledge acquisition is refined and then framed in form of ‘IF-Then’ variety of production rules. System modules are coded in AutoLISP language and user interface is created using visual basic (VB). The system is capable to automate various activities of process planning including blank modeling, blank nesting, determining punch force required, selection of clearance between punch and die, identifying sheet metal operations, and determining proper sequence of operations for manufacturing the part. The proposed system can be implemented on a PC having VB and AutoCAD software, therefore its low cost of implementation makes it affordable even for small scale sheet metal industries.     

Neural network method: delay and system of delay differential equations

In the present article, delay and system of delay differential equations are treated using feed-forward artificial neural networks. We have solved multiple problems using neural network architectures with different depths. The neural networks are trained using the extreme learning machine algorithm for the satisfaction of delay differential equations and associated initial/boundary conditions. Further, numerical rates of convergence of the proposed algorithm are reported based on variation of error in the obtained solution for different number of training points. Emphasis is on analysing whether deeper network architectures trained with extreme learning machine algorithm can perform better than shallow network architectures for approximating the solutions of delay differential equations.

     

Novel oil extraction technologies: Process conditions,quality parameters,and optimization

Conventional techniques of extracting oil using organic solvents pose health, safety, and environmental concerns. In modern extraction methods, green solvents such as water, ethanol, ethyl acetate, carbon dioxide, ionic liquids, and terpenes are currently gaining prominence. These green solvents present no signs of pollution and remain in liquid form over a temperature range of 0 to 140 °C. Other techniques covered in this review include microwave‐assisted enzymatic extraction, ultrasound‐assisted extraction, supercritical fluid technology, high pressure–assisted extraction, and pulse electric field–assisted extraction. These techniques are considered environmentally friendly because they exhibit less hazardous chemical synthesis, use renewable feedstock, and reduce the chemical load and emissions generated by organic solvents. Aqueous enzymatic extraction is a novel technique that uses enzymes as the medium for extraction of oil. Selection of the enzymes solely depends on the structure of the oilseed and the composition of the cell wall. Studies reveal an enzyme to substrate ratio of 1% to 8%, the temperature of 40 to 55 °C, and a pH of 4 to 8 to be typical for enzymatic extraction of oil from different oilseeds. Microwave‐assisted extraction has proven to impart significant effects on mass transfer and offers high throughput and extraction efficiency. A microwave power of 275 to 1,000 W and a temperature range of 30 to 60 °C are noticed in the different studies. The review presents a comprehensive account of the modern extraction techniques, the parameters responsible for yield and quality, and their industrial applications. Besides, the review highlights the optimized parameters for oil extraction from different oil‐bearing materials.     

Physicochemical characteristics,bioactive compounds and industrial applications of mango kernel and its products: A review

Mango (Mangifera indica L.) is a fruit plant of family Anacardiaceae, widely grown all over the world, and is a very popular fruit in the world market. Mango fruit is the second most traded tropical fruit and fifth in terms of production globally. Large quantities of mango processing coproducts are generated (peels and seeds), which usually are discarded as waste, yet are a potential source of fat, protein, carbohydrate, and certain bioactive compounds. Mango kernel is a remarkably rich source of macronutrients and micronutrients including calcium, potassium, magnesium, phosphorus, and vitamins A, E, K, and C. Phytochemicals with a notable therapeutic potential such as tocopherols, phytosterols, carotenoids, polyphenols (gallotannins, flavonols, benzophenone derivatives, mangiferin, homomangiferin, isomangiferin, anthocyanins, kaempferol, and quercetin), and phenolic acids (4‐caffeoylquinic acids, caffeic, coumaric, ellagic, gallic, and ferulic acid) are reported. The phytochemicals have high antioxidant, antimicrobial, anticancer, and, antiproliferation activities and could be used for food, cosmetic, and pharmaceutical applications. The nutritional composition of mango kernel constitutes 32.34% to 76.81% carbohydrate, 6% to 15.2% fat, 6.36% to 10.02% protein, 0.26% to 4.69% crude fiber, and 1.46% to 3.71% ash on a dry weight basis. The nutritional profile of the kernel suggests its usability as a food ingredient in the development of value‐added products such as mango kernel oil, mango kernel butter, mango kernel flour, and biofilms among other diverse products. This comprehensive systematic review explores mango kernel as a potential and novel food ingredient to meet the needs of a health‐conscious population. The review also provides a remedy to waste management and environmental pollution.