Analysis and Optimization of Machining Process Using Evolutionary Algorithms

To ensure quality of machined products at minimum machining costs and maximum machining effectiveness, it is very important to select optimum parameters when metal cutting machine tools are employed. Traditionally, the experience of the operator plays a major role in the selection of optimum metal cutting conditions. However, attaining optimum values each time by even a skilled operator is difficult. The non-linear nature of the machining process has compelled engineers to search for more effective methods to attain optimization. The design objective preceding most engineering design activities is simply to minimize the cost of production or to maximize the production efficiency. The main aim of research work reported here is to build robust optimization algorithms by exploiting ideas that nature has to offer from its backyard and using it to solve real world optimization problems in manufacturing processes.In this thesis, after conducting an exhaustive literature review, several optimization techniques used in various manufacturing processes have been identified. The selection of optimal cutting parameters, like depth of cut, feed and speed is a very important issue for every machining process. Experiments have been designed using Taguchi technique and dry turning of SS420 has been performed on Kirlosker turn master 35 lathe. Analysis using S/N and ANOVA were performed to find the optimum level and percentage of contribution of each parameter. By using S/N analysis the optimum machining parameters from the experimentation is obtained.Optimization algorithms begin with one or more design solutions supplied by the user and then iteratively check new design solutions, relative search spaces in order to achieve the true optimum solution. A mathematical model has been developed using response surface analysis for surface roughness and the model was validated using published results from literature.Methodologies in optimization such as Simulated annealing (SA), Particle Swarm Optimization (PSO), Conventional Genetic Algorithm (CGA) and Improved Genetic Algorithm (IGA) are applied to optimize machining parameters while dry turning of SS420 material. All the above algorithms were tested for their efficiency, robustness and accuracy and observe how they often outperform conventional optimization method applied to difficult real world problems. The SA, PSO, CGA and IGA codes were developed using MATLAB. For each evolutionary algorithmic method, optimum cutting conditions are provided to achieve better surface finish.The computational results using SA clearly demonstrated that the proposed solution procedure is quite capable in solving such complicated problems effectively and efficiently. Particle Swarm Optimization (PSO) is a relatively recent heuristic search method whose mechanics are inspired by the swarming or collaborative behavior of biological populations. From the results it has been observed that PSO provides better results and also more computationally efficient.Based on the results obtained using CGA and IGA for the optimization of machining process, the proposed IGA provides better results than the conventional GA. The improved genetic algorithm incorporating a stochastic crossover technique and an artificial initial population scheme is developed to provide a faster search mechanism. Finally, a comparison among these algorithms were made for the specific example of dry turning of SS 420 material and arriving at optimum machining parameters of feed, cutting speed, depth of cut and tool nose radius for minimum surface roughness as the criterion. To summarize, the research work fills in conspicuous gaps between research prototypes and industry requirements, by simulating evolutionary procedures seen in nature that optimize its own systems.

Reinforcement Learning Approaches to Power System Scheduling

One major component of power system operation is generation scheduling. The objective of the work is to develop efficient control strategies to the power scheduling problems through Reinforcement Learning approaches. The three important active power scheduling problems are Unit Commitment, Economic Dispatch and Automatic Generation Control. Numerical solution methods proposed for solution of power scheduling are insufficient in handling large and complex systems. Soft Computing methods like Simulated Annealing, Evolutionary Programming etc., are efficient in handling complex cost functions, but find limitation in handling stochastic data existing in a practical system. Also the learning steps are to be repeated for each load demand which increases the computation time.Reinforcement Learning (RL) is a method of learning through interactions with environment. The main advantage of this approach is it does not require a precise mathematical formulation. It can learn either by interacting with the environment or interacting with a simulation model. Several optimization and control problems have been solved through Reinforcement Learning approach. The application of Reinforcement Learning in the field of Power system has been a few. The objective is to introduce and extend Reinforcement Learning approaches for the active power scheduling problems in an implementable manner. The main objectives can be enumerated as:(i) Evolve Reinforcement Learning based solutions to the Unit Commitment Problem.(ii) Find suitable solution strategies through Reinforcement Learning approach for Economic Dispatch. (iii) Extend the Reinforcement Learning solution to Automatic Generation Control with a different perspective. (iv) Check the suitability of the scheduling solutions to one of the existing power systems.First part of the thesis is concerned with the Reinforcement Learning approach to Unit Commitment problem. Unit Commitment Problem is formulated as a multi stage decision process. Q learning solution is developed to obtain the optimwn commitment schedule. Method of state aggregation is used to formulate an efficient solution considering the minimwn up time I down time constraints. The performance of the algorithms are evaluated for different systems and compared with other stochastic methods like Genetic Algorithm.Second stage of the work is concerned with solving Economic Dispatch problem. A simple and straight forward decision making strategy is first proposed in the Learning Automata algorithm. Then to solve the scheduling task of systems with large number of generating units, the problem is formulated as a multi stage decision making task. The solution obtained is extended in order to incorporate the transmission losses in the system. To make the Reinforcement Learning solution more efficient and to handle continuous state space, a fimction approximation strategy is proposed. The performance of the developed algorithms are tested for several standard test cases. Proposed method is compared with other recent methods like Partition Approach Algorithm, Simulated Annealing etc.As the final step of implementing the active power control loops in power system, Automatic Generation Control is also taken into consideration.Reinforcement Learning has already been applied to solve Automatic Generation Control loop. The RL solution is extended to take up the approach of common frequency for all the interconnected areas, more similar to practical systems. Performance of the RL controller is also compared with that of the conventional integral controller.In order to prove the suitability of the proposed methods to practical systems, second plant ofNeyveli Thennal Power Station (NTPS IT) is taken for case study. The perfonnance of the Reinforcement Learning solution is found to be better than the other existing methods, which provide the promising step towards RL based control schemes for practical power industry.Reinforcement Learning is applied to solve the scheduling problems in the power industry and found to give satisfactory perfonnance. Proposed solution provides a scope for getting more profit as the economic schedule is obtained instantaneously. Since Reinforcement Learning method can take the stochastic cost data obtained time to time from a plant, it gives an implementable method. As a further step, with suitable methods to interface with on line data, economic scheduling can be achieved instantaneously in a generation control center. Also power scheduling of systems with different sources such as hydro, thermal etc. can be looked into and Reinforcement Learning solutions can be achieved.

Document Image Segmentation and Compression using Artificial Neural Networks and Evolutionary Methods

The work is intended to study the following important aspects of document image processing and develop new methods. (1) Segmentation ofdocument images using adaptive interval valued neuro-fuzzy method. (2) Improving the segmentation procedure using Simulated Annealing technique. (3) Development of optimized compression algorithms using Genetic Algorithm and parallel Genetic Algorithm (4) Feature extraction of document images (5) Development of IV fuzzy rules. This work also helps for feature extraction and foreground and background identification. The proposed work incorporates Evolutionary and hybrid methods for segmentation and compression of document images. A study of different neural networks used in image processing, the study of developments in the area of fuzzy logic etc is carried out in this work

A Reinforcement Learning Approach to Economic Dispatch using Neural Networks

This paper presents a Reinforcement Learning (RL) approach to economic dispatch (ED) using Radial Basis Function neural network. We formulate the ED as an N stage decision making problem. We propose a novel architecture to store Qvalues and present a learning algorithm to learn the weights of the neural network. Even though many stochastic search techniques like simulated annealing, genetic algorithm and evolutionary programming have been applied to ED, they require searching for the optimal solution for each load demand. Also they find limitation in handling stochastic cost functions. In our approach once we learn the Q-values, we can find the dispatch for any load demand. We have recently proposed a RL approach to ED. In that approach, we could find only the optimum dispatch for a set of specified discrete values of power demand. The performance of the proposed algorithm is validated by taking IEEE 6 bus system, considering transmission losses

New Simulated Corrugated Scaltering Surface Giving Widebandcharacter I Sti Cs

Simultaneous elimination of specular reflection and backscattered power from a plane metallic surface by simulated corrugated surfaces of constant period and variable strip width for TM polarisation is reported. This new configuration offers almost a ten-fold frequency bandwidth compared with a regularly spaced strip grating of the same size.

Aircraft down-range profiles formed from simulated and compact-range radar backscatter

Compact-range radar backscatter measurements are taken of aircraft scale models. In addition, computer software is used to predict the RCS of the aircraft. Synthetic down-range profiles formed from the two sources of backscatter data are compared and visualized in an innovative manner. Similar discrimination rates between the two aircraft are obtained on data from both source

Effect of annealing on the spectral and nonlinear optical characteristics of thin films of nano-ZnO

The annealing effect on the spectral and nonlinear optical NLO characteristics of ZnO thin films deposited on quartz substrates by sol-gel process is investigated. As the annealing temperature increases from 300–1050 °C, there is a decrease in the band gap, which indicates the changes of the interface of ZnO. ZnO is reported to show two emission bands, an ultraviolet UV emission band and another in the green region. The intensity of the UV peak remains the same while the intensity of the visible peak increases with increase in annealing temperature. The role of oxygen in ZnO thin films during the annealing process is important to the change in optical properties. The mechanism of the luminescence suggests that UV luminescence of ZnO thin films is related to the transition from conduction band edge to valence band, and green luminescence is caused by the transition from deep donor level to valence band due to oxygen vacancies. The NLO response of these samples is studied using nanosecond laser pulses at off-resonance wavelengths. The nonlinear absorption coefficient increases from 2.9 ×10−6 to 1.0 ×10−4 m/W when the annealing temperature is increased from 300 to 1050 °C, mainly due to the enhancement of interfacial state and exciton oscillator strength. The third order optical susceptibility x(3) increases with increase in annealing temperature (T) within the range of our investigations. In the weak confinement regime, T2.4 dependence of x(3) is obtained for ZnO thin films. The role of annealing temperature on the optical limiting response is also studied.

Fabrication of thin films and nano columnar structures of Fe-Ni amorphous alloys and modification of its surface properties by thermal annealing and swift heavy ion irradiation for tailoring the magnetic properties

Department of Physics, Cochin University of Science and Technology

Development of a new type of simulated scalar feed

This thesis presents the results of an investigation conducted for the development of a new type of feed horn antenna called "Simulated Scalar Feed". A schematic presentation of the work is given below. A review of the past important work done in the field of conventional/multimode electromagnetic horn antennas is presented in the first part of the second chapter. The work carried out on corrugated horns and surfaces are included in the second part of the review. In the third part, work on dielectric and dielectric loaded metal horns are reviewed. In all the parts of the review, special emphasis is given to theoretical design considerations. The methodology adopted for the experimental investigations is presented in the third chapter. The instrumentation utilized and thThis thesis presents the results of an investigation conducted for the development of a new type of feed horn antenna called "Simulated Scalar Feed". A schematic presentation of the work is given below. A review of the past important work done in the field of conventional/multimode electromagnetic horn antennas is presented in the first part of the second chapter. The work carried out on corrugated horns and surfaces are included in the second part of the review. In the third part, work on dielectric and dielectric loaded metal horns are reviewed. In all the parts of the review, special emphasis is given to theoretical design considerations. The methodology adopted for the experimental investigations is presented in the third chapter. The instrumentation utilized and the details of fabrication ofe details of fabrication of the new simulated scalar feed are described. The method of measurements of radiation characteristics of the antenna are also explained in this chapter. In the fourth chapter the outcome of the experimental results of the investigations carried out on horn antennas fabricated with different physical dimensions and different parameters for the E—plane boundary walls are highlighted. The theoretical explanation used to explain the experimental results is given in the fifth chapter of the thesis. A comparison between the experimental and the theoretical results is also presented in this chapter. In chapter six, the conclusions drawn from the experimental as well as the theoretical investigations are discussed. The advantages and features of the newly developed simulated scalar feed is examined in this chapter. Scope of further investigations in this field is also discussed at the end of this chapter.

On the Tailoring of Magnetic Properties of Fe-Based Alloy Thin Films by Swift Heavy Ion Irradiation and Thermal Annealing

The development of new materials has been the hall mark of human civilization. The quest for making new devices and new materials has prompted humanity to pursue new methods and techniques that eventually has given birth to modern science and technology. With the advent of nanoscience and nanotechnology, scientists are trying hard to tailor materials by varying their size and shape rather than playing with the composition of the material. This, along with the discovery of new and sophisticated imaging tools, has led to the discovery of several new classes of materials like (3D) Graphite, (2D) graphene, (1D) carbon nanotubes, (0D) fullerenes etc. Magnetic materials are in the forefront of applications and have beencontributing their share to remove obsolescence and bring in new devices based on magnetism and magnetic materials. They find applications in various devices such as electromagnets, read heads, sensors, antennas, lubricants etc. Ferromagnetic as well as ferrimagnetic materials have been in use in the form of various devices. Among the ferromagnetic materials iron, cobalt and nickel occupy an important position while various ferrites finds applications in devices ranging from magnetic cores to sensors.

Comparative efficacy of MS-222 and benzocaine as anaesthetics under simulated transport conditions of a tropical ornamental fish Puntius filamentosus(Valenciennes)

There is a growing commercial interest in the ¢sh, Puntius ¢lamentosus, in the ornamental ¢sh trade in India and elsewhere.The trade is, however, hampered by severe mortalities during transport of the ¢sh owing to insu⁄cient data available on the use of anaesthetics. To resolve this problem, we evaluated the e⁄cacy of two anaesthetics, MS-222 and benzocaine, in sedating P. ¢lamentosus in simulated transportation experiments and used stress response parameters such as cortisol and blood glucose levels to perform assessments. We observed that MS-222 at 40 mg L 1 and benzocaine at 20mg L 1 were su⁄- cient to induce sedation for 48 h. Above these concentrations, both the anaesthetics adversely a¡ected the ¢sh and resulted inmortalities. Both anaesthetics signi¢cantly lowered the blood cortisol and glucose levels compared with the unsedated controls. Importantly, the anaesthetics treatment signi¢cantly lowered the post-transport mortality in the ¢sh. The results of the study show that MS-222 and benzocaine could be used as sedatives to alleviate transport- related stress in P. ¢lamentosus to improve their post-transport survival and hence reduce economic loss.

Effect of thermal annealing on Fe40Ni38B18Mo4 thin films: modified Herzer model for magnetic evolution

Magnetic properties of nano-crystalline soft magnetic alloys have usually been correlated to structural evolution with heat treatment. However, literature reports pertaining to the study of nano-crystalline thin films are less abundant. Thin films of Fe40Ni38B18Mo4 were deposited on glass substrates under a high vacuum of ≈ 10−6 Torr by employing resistive heating. They were annealed at various temperatures ranging from 373 to 773K based on differential scanning calorimetric studies carried out on the ribbons. The magnetic characteristics were investigated using vibrating sample magnetometry. Morphological characterizations were carried out using atomic force microscopy (AFM), and magnetic force microscopy (MFM) imaging is used to study the domain characteristics. The variation of magnetic properties with thermal annealing is also investigated. From AFM and MFM images it can be inferred that the crystallization temperature of the as-prepared films are lower than their bulk counterparts. Also there is a progressive evolution of coercivity up to 573 K, which is an indication of the lowering of nano-crystallization temperature in thin films. The variation of coercivity with the structural evolution of the thin films with annealing is discussed and a plausible explanation is provided using the modified random anisotropy model

Annealing inducedlowcoercivity,nanocrystallineCo–Fe–Si thin films exhibitinginversecosine angular variation

Co–Fe–Si based films exhibit high magnetic moments and are highly sought after for applications like soft under layer sinper pendicular recording mediatomagneto-electro-mechanical sensor applications.In this workt he effect of annealing on s tructural,morphologicaland magnetic propertiesofco–Fe–Si thin films wasinvestigated.compositional analysis using x-rayphotoelectron spectroscopy and secondary ion massspectroscopyrevealedanativeoxidesurfacelayerconsistingofoxidesofco,feandsionthe surface. The morphology of theas deposited films shows mound like structures conformingtothe Volmer–Webergrowthmodel.Nanocrystallisationofamorphous films upon annealing was observed by glancing anglex-raydiffraction and transmission electron microscopy.Theevolutionofmagnetic properties with annealing is explained using the Herzermodel.Vibrating sample magnetometry measurements carried out at various angles from01 to 901 to the applied magnetic field were employed to study the angula rvariation of coercivity.The angular variation fits the modified Kondorsky model. Interestingly,the coercivity evolution with annealing deduced frommagneto-opticalKerreffectstudies indicates areversetrendcomparedtomagetisationobservedinthebulk.Thiscanbeattributedtoa domain wallpinningatnativeoxidelayeronthesurfaceofthin films. Theevolutionofsurfacemagnetic properties iscorrelatedwithmorphologyevolutionprobedusingatomicforcemicroscopy.The morphology aswellasthepresenceofthenativeoxidelayerdictatesthesurfacemagneticproperties and this is corroborated by the apparent difference in the bulk and surface magnetic properties

Structural, topographical and magnetic evolution of RF-sputtered Fe-Ni alloy based thin films with thermal annealing

Metglas 2826 MB having a nominal composition of Fe40Ni38Mo4B18 is an excellent soft magnetic material and finds application in sensors and memory heads. However, the thin-film forms of Fe40Ni38Mo4B18 are seldom studied, although they are important in micro-electro-mechanical systems/nano-electromechanical systems devices. The stoichiometry of the film plays a vital role in determining the structural and magnetic properties of Fe40Ni38Mo4B18 thin films: retaining the composition in thin films is a challenge. Thin films of 52 nm thickness were fabricated by RF sputtering technique on silicon substrate from a target of nominal composition of Fe40Ni38Mo4B18. The films were annealed at temperatures of 400 °C and 600 °C. The micro-structural studies of films using glancing x-ray diffractometer (GXRD) and transmission electron microscope (TEM) revealed that pristine films are crystalline with (FeNiMo)23B6 phase. Atomic force microscope (AFM) images were subjected to power spectral density analysis to understand the probable surface evolution mechanism during sputtering and annealing. X-ray photoelectron spectroscopy (XPS) was employed to determine the film composition. The sluggish growth of crystallites with annealing is attributed to the presence of molybdenum in the thin film. The observed changes in magnetic properties were correlated with annealing induced structural, compositional and morphological changes

Evolution of structural and magnetic properties of Co–Fe based metallic glass thin films with thermal annealing

Ultra thin films based on CoFe were prepared from a composite target employing thermal evaporation. The microstructure of the films was modified by thermal annealing. The relationship between microstructure and magnetic properties of the films was investigated using techniques like glancing angle X-ray diffraction (GXRD), transmission electron microscopy (TEM) and vibrating sample magnetometry (VSM). The GXRD and TEM investigations showed an onset of crystallization of CoFe at around 373 K. The magnetic softness of the films improved with thermal annealing but at higher annealing temperature it is found to be deteriorating. Annealing inducedmodification of surface morphology of the alloy thin filmswas probed by atomic force microscopy (AFM). Surface smoothening was observed with thermal annealing and the observed magnetic properties correlate well with surface modifications induced by thermal annealing