Search results for: discrete optimization

Authors: Ouahab Kadri, Leila Hayet Mouss

Abstract:

In this paper, we present three diagnostic modules for complex and dynamic systems. These modules are based on three ant colony algorithms, which are AntTreeStoch, Lumer & Faieta and Binary ant colony. We chose these algorithms for their simplicity and their wide application range. However, we cannot use these algorithms in their basement forms as they have several limitations. To use these algorithms in a diagnostic system, we have proposed three variants. We have tested these algorithms on datasets issued from two industrial systems, which are clinkering system and pasteurization system.

Keywords: ant colony algorithms, complex and dynamic systems, diagnosis, classification, optimization

Procedia PDF Downloads 298

Authors: Andrey V. Timofeev, Dmitry V. Egorov

Abstract:

This paper introduces an original method of parametric optimization of the structure for multimodal decision-level fusion scheme which combines the results of the partial solution of the classification task obtained from assembly of the mono-modal classifiers. As a result, a multimodal fusion classifier which has the minimum value of the total error rate has been obtained.

Keywords: classification accuracy, fusion solution, total error rate, multimodal fusion classifier

Procedia PDF Downloads 466

Authors: Ashwini Gowda K. S, Archana M. R, Anjaneyappa V

Abstract:

This paper presents pavement maintenance and management system (PMMS) to obtain optimum pavement maintenance and rehabilitation strategies and maintenance scheduling for a network using a multi-objective genetic algorithm (MOGA). Optimal pavement maintenance & rehabilitation strategy is to maximize the pavement condition index of the road section in a network with minimum maintenance and rehabilitation cost during the planning period. In this paper, NSGA-II is applied to perform maintenance optimization; this maintenance approach was expected to preserve and improve the existing condition of the highway network in a cost-effective way. The proposed PMMS is applied to a network that assessed pavement based on the pavement condition index (PCI). The minimum and maximum maintenance cost for a planning period of 20 years obtained from the non-dominated solution was found to be 5.190x10¹⁰ ₹ and 4.81x10¹⁰ ₹, respectively.

Keywords: genetic algorithm, maintenance and rehabilitation, optimization technique, pavement condition index

Procedia PDF Downloads 149

Authors: Soudabeh Shemehsavar

Abstract:

In this paper, we consider the situation under a life test, in which the failure time of the test units are not related deterministically to an observable stochastic time varying covariate. In such a case, the joint distribution of failure time and a marker value would be useful for modeling the step stress life test. The problem of accelerating such an experiment is considered as the main aim of this paper. We present a step stress accelerated model based on a bivariate Wiener process with one component as the latent (unobservable) degradation process, which determines the failure times and the other as a marker process, the degradation values of which are recorded at times of failure. Parametric inference based on the proposed model is discussed and the optimization procedure for obtaining the optimal time for changing the stress level is presented. The optimization criterion is to minimize the approximate variance of the maximum likelihood estimator of a percentile of the products’ lifetime distribution.

Keywords: bivariate normal, Fisher information matrix, inverse Gaussian distribution, Wiener process

Procedia PDF Downloads 317

Authors: Majid Arvan, Peyman Beygi, Sina Rokhsati

Abstract:

In-time detection of fire in buildings is of great importance. Employing intelligent methods in data processing in fire detection systems leads to a significant reduction of fire damage at lowest cost. In this paper, the raw data obtained from the fire detection sensor networks in buildings is processed by using intelligent methods based on neural networks and the likelihood of fire happening is predicted. In order to enhance the quality of system, the noise in the sensor data is reduced by analyzing wavelets and applying SVD technique. Meanwhile, the proposed neural network is trained using particle swarm optimization (PSO). In the simulation work, the data is collected from sensor network inside the room and applied to the proposed network. Then the outputs are compared with conventional MLP network. The simulation results represent the superiority of the proposed method over the conventional one.

Keywords: intelligent fire detection, neural network, particle swarm optimization, fire sensor network

Procedia PDF Downloads 380

Authors: Pooja Rani, G. S. Mahapatra, S. K. Pandey

Abstract:

In this paper, we propose a novel approach of Neural Network and Particle Swarm Optimization methods for software reliability prediction. We first explain how to apply compound function in neural network so that we can derive a Flexible Logistic (S-shaped) Growth Curve (FLGC) model. This model mathematically represents software failure as a random process and can be used to evaluate software development status during testing. To avoid trapping in local minima, we have applied Particle Swarm Optimization method to train proposed model using failure test data sets. We drive our proposed model using computational based intelligence modeling. Thus, proposed model becomes Neuro-Particle Swarm Optimization (NPSO) model. We do test result with different inertia weight to update particle and update velocity. We obtain result based on best inertia weight compare along with Personal based oriented PSO (pPSO) help to choose local best in network neighborhood. The applicability of proposed model is demonstrated through real time test data failure set. The results obtained from experiments show that the proposed model has a fairly accurate prediction capability in software reliability.

Keywords: software reliability, flexible logistic growth curve model, software cumulative failure prediction, neural network, particle swarm optimization

Procedia PDF Downloads 344

Authors: James Adewale, Joshua Sunday

Abstract:

In this paper, we developed a linear multistep method, which is implemented in predictor corrector-method. The corrector is developed by method of collocation and interpretation of power series approximate solutions at some selected grid points, to give a continuous linear multistep method, which is evaluated at some selected grid points to give a discrete linear multistep method. The predictors were also developed by method of collocation and interpolation of power series approximate solution, to give a continuous linear multistep method. The continuous linear multistep method is then solved for the independent solution to give a continuous block formula, which is evaluated at some selected grid point to give discrete block method. Basic properties of the corrector were investigated and found to be zero stable, consistent and convergent. The efficiency of the method was tested on some linear, non-learn, oscillatory and stiff problems of first order, initial value problems of ordinary differential equations. The results were found to be better in terms of computer time and error bound when compared with the existing methods.

Keywords: predictor, corrector, collocation, interpolation, approximate solution, independent solution, zero stable, consistent, convergent

Procedia PDF Downloads 501

Authors: Jin Ho Kim, Yujeong Shin, Seong-Jin Cho, Dong-Jin Kim, U-Syn Ha

Abstract:

Due to the development of the information industry and technologies, cellular phones have must not only function to communicate, but also have functions such as the Internet, e-banking, entertainment, etc. These phones are called smartphones. The performance of smartphones has improved, because of the various functions of smartphones, and the capacity of the battery has been increased gradually. Recently, linear generators have been embedded in smartphones in order to recharge the smartphone's battery. In this study, optimization is performed and an array change of permanent magnets is examined in order to increase efficiency. We propose an optimal design using design of experiments (DOE) to maximize the generated induced voltage. The thickness of the poleshoe and permanent magnet (PM), the height of the poleshoe and PM, and the thickness of the coil are determined to be design variables. We made 25 sampling points using an orthogonal array according to four design variables. We performed electromagnetic finite element analysis to predict the generated induced voltage using the commercial electromagnetic analysis software ANSYS Maxwell. Then, we made an approximate model using the Kriging algorithm, and derived optimal values of the design variables using an evolutionary algorithm. The commercial optimization software PIAnO (Process Integration, Automation, and Optimization) was used with these algorithms. The result of the optimization shows that the generated induced voltage is improved.

Keywords: smartphone, linear generator, design of experiment, approximate model, optimal design

Procedia PDF Downloads 345

Authors: Ahmed Elrewainy

Abstract:

Mixing in the hyperspectral imaging occurs due to the low spatial resolutions of the used cameras. The existing pure materials “endmembers” in the scene share the spectra pixels with different amounts called “abundances”. Unmixing of the data cube is an important task to know the present endmembers in the cube for the analysis of these images. Unsupervised unmixing is done with no information about the given data cube. Sparsity is one of the recent approaches used in the source recovery or unmixing techniques. The l₁-norm optimization problem “basis pursuit” could be used as a sparsity-based approach to solve this unmixing problem where the endmembers is assumed to be sparse in an appropriate domain known as dictionary. This optimization problem is solved using proximal method “iterative thresholding”. The l₁-norm basis pursuit optimization problem as a sparsity-based unmixing technique was used to unmix real and synthetic hyperspectral data cubes.

Keywords: basis pursuit, blind source separation, hyperspectral imaging, spectral unmixing, wavelets

Procedia PDF Downloads 195

Authors: Louis N. Y. Wong

Abstract:

En-echelon fractures are commonly found in rocks, which appear as a special set of regularly oriented and spaced fractures. By using both experimental and numerical approaches, this study investigates the interaction among them, and how this interaction finally contributes to the development of a shear rupture (fault), especially in brittle natural rocks. Firstly, uniaxial compression tests are conducted on marble specimens containing en-echelon flaws. The latter is cut by using the water abrasive jet into the rock specimens. The fracturing processes of these specimens leading to the formation of a fault are observed in detail by the use of a high speed camera. The influences of the flaw geometry on the production of tensile cracks and shear cracks, which in turn dictate the coalescence patterns of the entire set of en-echelon flaws are comprehensively studied. Secondly, a numerical study based on a recently developed contact model, flat-joint contact model using the discrete element method (DEM) is carried out to model the present laboratory experiments. The numerical results provide a quantitative assessment of the interaction of en-echelon flaws. Particularly, the evolution of the stress field, as well as the characteristics of new crack initiation, propagation and coalescence associated with the generation of an eventual shear rupture are studied in detail. The numerical results are found to agree well with the experimental results obtained in both microscopic and macroscopic observations.

Keywords: discrete element method, en-echelon flaws, fault, marble

Procedia PDF Downloads 255

Authors: Mohammad H. Almomani

Abstract:

In this paper, we argue the effect of the initial sample size, and the increment in simulation samples on the performance of a sequential approach that used in selecting the top m designs when the number of alternative designs is very large. The sequential approach consists of two stages. In the first stage the ordinal optimization is used to select a subset that overlaps with the set of actual best k% designs with high probability. Then in the second stage the optimal computing budget is used to select the top m designs from the selected subset. We apply the selection approach on a generic example under some parameter settings, with a different choice of initial sample size and the increment in simulation samples, to explore the impacts on the performance of this approach. The results show that the choice of initial sample size and the increment in simulation samples does affect the performance of a selection approach.

Keywords: Large Scale Problems, Optimal Computing Budget Allocation, ordinal optimization, simulation optimization

Procedia PDF Downloads 355

Authors: Yihao Kuang, Bowen Ding

Abstract:

With the increasing scale and complexity of knowledge graph, modern knowledge graph contains more and more types of entity, relationship, and attribute information. Therefore, in recent years, it has been a trend for knowledge graph inference to use reinforcement learning to deal with large-scale, incomplete, and noisy knowledge graphs and improve the inference effect and interpretability. The Proximal Policy Optimization (PPO) algorithm utilizes a near-end strategy optimization approach. This allows for more extensive updates of policy parameters while constraining the update extent to maintain training stability. This characteristic enables PPOs to converge to improved strategies more rapidly, often demonstrating enhanced performance early in the training process. Furthermore, PPO has the advantage of offline learning, effectively utilizing historical experience data for training and enhancing sample utilization. This means that even with limited resources, PPOs can efficiently train for reinforcement learning tasks. Based on these characteristics, this paper aims to obtain a better and more efficient inference effect by introducing PPO into knowledge inference technology.

Keywords: reinforcement learning, PPO, knowledge inference

Procedia PDF Downloads 242

Authors: Sule Yucelbas, Gulay Tezel, Cuneyt Yucelbas, Seral Ozsen

Abstract:

In this study, it was tried to identify some heart rhythm disorders by electrocardiography (ECG) data that is taken from MIT-BIH arrhythmia database by subtracting the required features, presenting to artificial neural networks (ANN), artificial immune systems (AIS), artificial neural network based on artificial immune system (AIS-ANN) and particle swarm optimization based artificial neural network (PSO-NN) classifier systems. The main purpose of this study is to evaluate the performance of hybrid AIS-ANN and PSO-ANN classifiers with regard to the ANN and AIS. For this purpose, the normal sinus rhythm (NSR), atrial premature contraction (APC), sinus arrhythmia (SA), ventricular trigeminy (VTI), ventricular tachycardia (VTK) and atrial fibrillation (AF) data for each of the RR intervals were found. Then these data in the form of pairs (NSR-APC, NSR-SA, NSR-VTI, NSR-VTK and NSR-AF) is created by combining discrete wavelet transform which is applied to each of these two groups of data and two different data sets with 9 and 27 features were obtained from each of them after data reduction. Afterwards, the data randomly was firstly mixed within themselves, and then 4-fold cross validation method was applied to create the training and testing data. The training and testing accuracy rates and training time are compared with each other. As a result, performances of the hybrid classification systems, AIS-ANN and PSO-ANN were seen to be close to the performance of the ANN system. Also, the results of the hybrid systems were much better than AIS, too. However, ANN had much shorter period of training time than other systems. In terms of training times, ANN was followed by PSO-ANN, AIS-ANN and AIS systems respectively. Also, the features that extracted from the data affected the classification results significantly.

Keywords: AIS, ANN, ECG, hybrid classifiers, PSO

Procedia PDF Downloads 442

Authors: Ali Shirazi, Robert A. Taylor, Stephen D. White, Graham L. Morrison

Abstract:

In this paper, a detailed simulation model of a solar-powered triple-effect LiBr–H₂O absorption chiller is developed to supply both cooling and heating demand of a large-scale building, aiming to reduce the fossil fuel consumption and greenhouse gas emissions in building sector. TRNSYS 17 is used to simulate the performance of the system over a typical year. A combined energetic-economic-environmental analysis is conducted to determine the system annual primary energy consumption and the total cost, which are considered as two conflicting objectives. A multi-objective optimization of the system is performed using a genetic algorithm to minimize these objectives simultaneously. The optimization results show that the final optimal design of the proposed plant has a solar fraction of 72% and leads to an annual primary energy saving of 0.69 GWh and annual CO₂ emissions reduction of ~166 tonnes, as compared to a conventional HVAC system. The economics of this design, however, is not appealing without public funding, which is often the case for many renewable energy systems. The results show that a good funding policy is required in order for these technologies to achieve satisfactory payback periods within the lifetime of the plant.

Keywords: economic, environmental, multi-objective optimization, solar air-conditioning, triple-effect absorption chiller

Procedia PDF Downloads 238

Authors: Junjie Peng, Jinbao Chen, Shuai Kong, Danxu Liu

Abstract:

On the basis of traditional resource allocation strategies, the usage of resources on physical servers in cloud data center is great uncertain. It will cause waste of resources if the assignment of tasks is not enough. On the contrary, it will cause overload if the assignment of tasks is too much. This is especially obvious when the applications are the same type because of its resource preferences. Considering CPU intensive application is one of the most common types of application in the cloud, we studied the optimization strategy for CPU intensive applications on the same server. We used resource preferences to analyze the case that multiple CPU intensive applications run simultaneously, and put forward a model which can predict the execution time for CPU intensive applications which run simultaneously. Based on the prediction model, we proposed the method to select the appropriate number of applications for a machine. Experiments show that the model can predict the execution time accurately for CPU intensive applications. To improve the execution efficiency of applications, we propose a scheduling model based on priority for CPU intensive applications. Extensive experiments verify the validity of the scheduling model.

Keywords: cloud computing, CPU intensive applications, resource optimization, strategy

Procedia PDF Downloads 278

Authors: Tahsin A. H. Nishat, Raquib Ahsan

Abstract:

Sensitivity analysis of design parameters of the optimization procedure can become a significant factor while designing any structural system. The objectives of the study are to analyze the sensitivity of deck slab thickness parameter obtained from both the conventional and optimum design methodology of pre-stressed post-tensioned I-girder and deck system and to compare the relative significance of slab thickness. For analysis on conventional method, the values of 14 design parameters obtained by the conventional iterative method of design of a real-life I-girder bridge project have been considered. On the other side for analysis on optimization method, cost optimization of this system has been done using global optimization methodology 'Evolutionary Operation (EVOP)'. The problem, by which optimum values of 14 design parameters have been obtained, contains 14 explicit constraints and 46 implicit constraints. For both types of design parameters, sensitivity analysis has been conducted on deck slab thickness parameter which can become too sensitive for the obtained optimum solution. Deviations of slab thickness on both the upper and lower side of its optimum value have been considered reflecting its realistic possible ranges of variations during construction. In this procedure, the remaining parameters have been kept unchanged. For small deviations from the optimum value, compliance with the explicit and implicit constraints has been examined. Variations in the cost have also been estimated. It is obtained that without violating any constraint deck slab thickness obtained by the conventional method can be increased up to 25 mm whereas slab thickness obtained by cost optimization can be increased only up to 0.3 mm. The obtained result suggests that slab thickness becomes less sensitive in case of conventional method of design. Therefore, for realistic design purpose sensitivity should be conducted for any of the design procedure of girder and deck system.

Keywords: sensitivity analysis, optimum design, evolutionary operations, PC I-girder, deck system

Procedia PDF Downloads 137

Authors: Tareq Hamadneh, Jochen Merker, Hassan Al-Zoubi

Abstract:

Bernstein's expansion for exponentials in Taylor functions provides lower and upper optimization values for the range of its original function. these values converge to the original functions if the degree is elevated or the domain subdivided. Taylor polynomial can be applied so that the exponential is a polynomial of finite degree over a given domain. Bernstein's basis has two main properties: its sum equals 1, and positive for all x 2 (0; 1). In this work, we prove the existence of fixed points for exponential functions in a given domain using the optimization values of Bernstein. The Bernstein basis of finite degree T over a domain D is defined non-negatively. Any polynomial p of degree t can be expanded into the Bernstein form of maximum degree t ≤ T, where we only need to compute the coefficients of Bernstein in order to optimize the original polynomial. The main property is that p(x) is approximated by the minimum and maximum Bernstein coefficients (Bernstein bound). If the bound is contained in the given domain, then we say that p(x) has fixed points in the same domain.

Keywords: Bernstein polynomials, Stability of control functions, numerical optimization, Taylor function

Procedia PDF Downloads 135

Authors: Karim Farahmandfar, Hamidolah Izadi, Mohammadreza Rezaei, Amin Ardali, Ebrahim Goshtasbi Rad, Khosro Jafarpoor

Abstract:

Statistics illustrates that the higher amount of annual energy consumption is related to surmounting the demand in buildings. Therefore, it is vital to economize the energy consumption and also find the solution with regard to this issue. One of the systems for the sake of heating the building is floor heating. As a matter of fact, floor heating performance is based on convection and radiation. Actually, in addition to creating a favorable heating condition, this method leads to energy saving. It is the goal of this article to outline the constructal theory and introduce the optimization method in branch networks for floor heating. There are several steps in order to gain this purpose. First of all, the pressure drop through the two points of the network is calculated. This pressure drop is as a function of pipes diameter and other parameters. After that, the amount of heat transfer is determined. Consequently, as a result of the combination of these two functions, the final function will be determined. It is necessary to mention that flow is laminar.

Keywords: constructal theory, optimization, floor heating system, turbulent flow

Procedia PDF Downloads 319

Authors: Swarali Hingse, Shraddha Digole, Uday Annapure

Abstract:

The present study investigates the biotransformation of ferulic acid to vanillin by Pycnoporus cinnabarinus and its optimization using one-factor-at-a-time method as well as statistical approach. Effect of various physicochemical parameters and medium components was studied using one-factor-at-a-time method. Screening of the significant factors was carried out using L25 Taguchi orthogonal array and then these selected significant factors were further optimized using response surface methodology (RSM). Significant media components obtained using Taguchi L25 orthogonal array were glucose, KH2PO4 and yeast extract. Further, a Box Behnken design was used to investigate the interactive effects of the three most significant media components. The final medium obtained after optimization using RSM containing glucose (34.89 g/L), diammonium tartrate (1 g/L), yeast extract (1.47 g/L), MgSO4•7H2O (0.5 g/L), KH2PO4 (0.15 g/L), and CaCl2•2H2O (20 mg/L) resulted in amplification of vanillin production from 30.88 mg/L to 187.63 mg/L.

Keywords: ferulic acid, pycnoporus cinnabarinus, response surface methodology, vanillin

Procedia PDF Downloads 383

Authors: Archana Thangavelu, Han-Ik Park, Young-Chul Park, Joon-Hong Park

Abstract:

In this numerical study, we have proposed a method for evaluation of backward extrusion process of pressure vessel made up of steel. Demand for lighter and stiffer products have been increasing in the last years especially in automobile engineering. Through detailed finite element analysis, effective stress, strain and velocity profile have been obtained with optimal range. The process design of a forward and backward extrusion axe-symmetric part has been studied. Forging is mainly carried out because forged products are highly reliable and possess superior mechanical properties when compared to normal products. Performing computational simulations of 3D hot forging with various dimensions of billet and optimization of weight is carried out using Taguchi Orthogonal Array (OA) Optimization technique. The technique used in this study can be used for newly developed materials to investigate its forgeability for much complicated shapes in closed hot die forging process.

Keywords: backward extrusion, hot forging, optimization, finite element analysis, Taguchi method

Procedia PDF Downloads 309

Authors: Xuran Zhang, Huiru Chen

Abstract:

In recent years, China has made great efforts to cultivate and develop the housing rental market, especially the rental-type public housing, which has been paid attention to by all sectors of the society. This paper takes Hangzhou rental-type public housing as the research object, and divides it into three development stages according to the different supply modes of rental-type public housing. Through data collection and field research, the paper summarizes the spatial characteristics of rental-type public housing from the five perspectives of spatial planning, spatial layout, spatial integration, spatial organization and spatial configuration. On this basis, the paper proposes the optimization of the spatial layout. The study concludes that the spatial layout of rental-type public housing should be coordinated with the development of urban planning. When planning and constructing, it is necessary to select more mixed construction modes, to be properly centralized, and to improve the surrounding transportation service facilities.  It is hoped that the recommendations in this paper will provide a reference for the further development of rental-type public housing in Hangzhou.

Keywords: Hangzhou, rental-type public housing, spatial distribution, spatial optimization

Procedia PDF Downloads 323

Authors: Lela Pintarić, Iva Rezić, Ana Vrsalović Presečki

Abstract:

Considering an enormous increase of the use of metal nanoparticles with the exactly defined characteristics, the main goal of this research was to found the optimal and environmental friendly method of their synthesis. The synthesis of the inorganic core-shell nanoparticles was optimized as a model. The core-shell nanoparticles are composed of the enzyme core belted with the metal ions, oxides or salts as a shell. In this research, enzyme urease was the core catalyst and the shell nanoparticle was made of silver. Silver nanoparticles are widespread utilized and some of their common uses are: as an addition to disinfectants to ensure an aseptic environment for the patients, as a surface coating for neurosurgical shunts and venous catheters, as an addition to implants, in production of socks for diabetics and athletic clothing where they improve antibacterial characteristics, etc. Characteristics of synthesized nanoparticles directly depend on of their size, so the special care during this optimization was given to the determination of the size of the synthesized nanoparticles. For the purpose of the above mentioned optimization, sixteen experiments were generated by the Design of Experiments (DoE) method and conducted under various temperatures, with different initial concentration of the silver nitrate and constant concentration of the urease of two separate manufacturers. Synthesized nanoparticles were analyzed by the Nanoparticle Tracking Analysis (NTA) method on Malvern NanoSight NS300. Results showed that the initial concentration of the silver ions does not affect the concentration of the synthesized silver nanoparticles neither their size distribution. On the other hand, temperature of the experiments has affected both of the mentioned values.

Keywords: core-shell nanoparticles, optimization, silver, urease

Procedia PDF Downloads 313

Authors: Willi Zschiebsch, Alrik Dargel, Sebastian Spitzer, Philipp Johst, Robert Böhm, Niels Modler

Abstract:

In this article, we investigate an approach that digitally links individual development process steps by using the drive shaft of an aircraft engine as a representative example of a fiber polymer composite. Such high-performance, lightweight composite structures have many adjustable parameters that influence the mechanical properties. Only a combination of optimal parameter values can lead to energy efficient lightweight structures. The development tools required for the Engineering Design Process (EDP) are often isolated solutions, and their compatibility with each other is limited. A digital framework is presented in this study, which allows individual specialised tools to be linked via the generated data in such a way that automated optimization across programs becomes possible. This is demonstrated using the example of linking geometry generation with numerical structural analysis. The proposed digital framework for automated design optimization demonstrates the feasibility of developing a complete digital approach to design optimization. The methodology shows promising potential for achieving optimal solutions in terms of mass, material utilization, eigenfrequency, and deformation under lateral load with less development effort. The development of such a framework is an important step towards promoting a more efficient design approach that can lead to stable and balanced results.

Keywords: digital linked process, composite, CFRP, multi-objective, EDP, NSGA-2, NSGA-3, TPE

Procedia PDF Downloads 76

Authors: Yihao Kuang, Bowen Ding

Abstract:

With the increasing scale and complexity of knowledge graph, modern knowledge graph contains more and more types of entity, relationship, and attribute information. Therefore, in recent years, it has been a trend for knowledge graph inference to use reinforcement learning to deal with large-scale, incomplete, and noisy knowledge graph and improve the inference effect and interpretability. The Proximal Policy Optimization (PPO) algorithm utilizes a near-end strategy optimization approach. This allows for more extensive updates of policy parameters while constraining the update extent to maintain training stability. This characteristic enables PPOs to converge to improve strategies more rapidly, often demonstrating enhanced performance early in the training process. Furthermore, PPO has the advantage of offline learning, effectively utilizing historical experience data for training and enhancing sample utilization. This means that even with limited resources, PPOs can efficiently train for reinforcement learning tasks. Based on these characteristics, this paper aims to obtain better and more efficient inference effect by introducing PPO into knowledge inference technology.

Keywords: reinforcement learning, PPO, knowledge inference, supervised learning

Procedia PDF Downloads 67

Authors: Dominika Crnjac Milic, Martina Martinovic, Vladimir Simovic

Abstract:

The case study method in this paper shows the implementation of Information Technology (IT) and the Serial Shipping Container Code (SSCC) in a Croatian company that deals with logistics operations and provides logistics services in the cold chain segment. This company is aware of the sensitivity of the goods entrusted to them by the user of the service, as well as of the importance of speed and accuracy in providing logistics services. To that end, it has implemented and used the latest IT to ensure the highest standard of high-quality logistics services to its customers. Looking for efficiency and optimization of supply chain management, while maintaining a high level of quality of the products that are sold, today's users of outsourced logistics services are open to the implementation of new IT products that ultimately deliver savings. By analysing the positive results and the difficulties that arise when using this technology, we aim to provide an insight into the potential of this approach of the logistics service provider.

Keywords: logistics operations, serial shipping container code, information technology, cost optimization

Procedia PDF Downloads 360

Authors: Qianqian He, Naian Liu, Xiaodong Xie, Linhe Zhang, Yang Zhang, Weidong Yan

Abstract:

In the wild, the vegetation layer with exceptionally complex fuel composition and heterogeneous spatial distribution strongly affects the rate of fire spread (ROS) and fire intensity. Clarifying the influence of fuel bed structure on fire spread behavior is of great significance to wildland fire management and prediction. The packing ratio is one of the key physical parameters describing the property of the fuel bed. There is a threshold value of the packing ratio for ROS, but little is known about the controlling mechanism. In this study, to address this deficiency, a series of fire spread experiments were performed across a discrete fuel bed composed of some regularly arranged laser-cut cardboards, with constant wind speed and different packing ratios (0.0125-0.0375). The experiment aims to explore the relative importance of the internal and surface heat transfer with packing ratio. The dependence of the measured ROS on the packing ratio was almost consistent with the previous researches. The data of the radiative and total heat fluxes show that the internal heat transfer and surface heat transfer are both enhanced with increasing packing ratio (referred to as ‘Stage 1’). The trend agrees well with the variation of the flame length. The results extracted from the video show that the flame length markedly increases with increasing packing ratio in Stage 1. Combustion intensity is suggested to be increased, which, in turn, enhances the heat radiation. The heat flux data shows that the surface heat transfer appears to be more important than the internal heat transfer (fuel preheating inside the fuel bed) in Stage 1. On the contrary, the internal heat transfer dominates the fuel preheating mechanism when the packing ratio further increases (referred to as ‘Stage 2’) because the surface heat flux keeps almost stable with the packing ratio in Stage 2. As for the heat convection, the flow velocity was measured using Pitot tubes both inside and on the upper surface of the fuel bed during the fire spread. Based on the gas velocity distribution ahead of the flame front, it is found that the airflow inside the fuel bed is restricted in Stage 2, which can reduce the internal heat convection in theory. However, the analysis indicates not the influence of inside flow on convection and combustion, but the decreased internal radiation of per unit fuel is responsible for the decrease of ROS.

Keywords: discrete fuel bed, fire spread, packing ratio, wildfire

Procedia PDF Downloads 142

Authors: Essa Abrahim Abdulgader Saleem, Thien-My Dao

Abstract:

The main objective of this paper is to optimize series-parallel system reliability using Genetic Algorithm (GA) and statistical analysis; considering system reliability constraints which involve the redundant numbers of selected components, total cost, and total weight. To perform this work, firstly the mathematical model which maximizes system reliability subject to maximum system cost and maximum system weight constraints is presented; secondly, a statistical analysis is used to optimize GA parameters, and thirdly GA is used to optimize series-parallel systems reliability. The objective is to determine the strategy choosing the redundancy level for each subsystem to maximize the overall system reliability subject to total cost and total weight constraints. Finally, the series-parallel system case study reliability optimization results are showed, and comparisons with the other previous results are presented to demonstrate the performance of our GA.

Keywords: reliability, optimization, meta-heuristic, genetic algorithm, redundancy

Procedia PDF Downloads 337

Authors: E. Tandis, E. Assareh

Abstract:

Designing the optimal shape of MW wind turbine blades is provided in a number of cases through evolutionary algorithms associated with mathematical modeling (Blade Element Momentum Theory). Evolutionary algorithms, among the optimization methods, enjoy many advantages, particularly in stability. However, they usually need a large number of function evaluations. Since there are a large number of local extremes, the optimization method has to find the global extreme accurately. The present paper introduces a new population-based hybrid algorithm called Genetic-Based Bees Algorithm (GBBA). This algorithm is meant to design the optimal shape for MW wind turbine blades. The current method employs crossover and neighborhood searching operators taken from the respective Genetic Algorithm (GA) and Bees Algorithm (BA) to provide a method with good performance in accuracy and speed convergence. Different blade designs, twenty-one to be exact, were considered based on the chord length, twist angle and tip speed ratio using GA results. They were compared with BA and GBBA optimum design results targeting the power coefficient and solidity. The results suggest that the final shape, obtained by the proposed hybrid algorithm, performs better compared to either BA or GA. Furthermore, the accuracy and speed convergence increases when the GBBA is employed

Keywords: Blade Design, Optimization, Genetic Algorithm, Bees Algorithm, Genetic-Based Bees Algorithm, Large Wind Turbine

Procedia PDF Downloads 316

Authors: Ali Ramezani

Abstract:

Balancing feeding system of plastic injection molding has overriding importance as it minimizes the process’s product defects such as weld line, shrinkage, sink marks and warpage. This article presents the difference between optimization of feeding system in identical multi-cavity molding and family molding using Moldflow Plastic Insight software. In this work, the effect of dimension, shape, position and type of gates and runners on the products quality was studied. The optimization was carried out by analyzing plastic injection molding process parameters, including melt temperature, mold temperature, cooling time, cooling temperature packing time and packing pressure. It was found that symmetrical feeding system is the most efficient shape for diminishing defects in identical multi-cavity molding. However, the same results were not concluded for family molding due to the differences between volume, mass, thickness and shape of cavities.

Keywords: balancing feeding system, family molding, multi-cavity, Moldflow, plastic injection

Procedia PDF Downloads 135

Authors: Seyed Sadegh Naseralavi, Mohsen Khatibinia

Abstract:

In structural optimizations through meta-heuristic algorithms, analyses of structures are performed for many times. For this reason, performing the analyses in a time saving way is precious. The importance of the point is more accentuated in time-history analyses which take much time. To this aim, peak picking methods also known as spectrum analyses are generally utilized. However, such methods do not have the required accuracy either done by square root of sum of squares (SRSS) or complete quadratic combination (CQC) rules. The paper presents an efficient technique for evaluating the dynamic responses during the optimization process with high speed and accuracy. In the method, first by using a static equivalent of the earthquake, an initial design is obtained. Then, the displacements in the modal coordinates are achieved. The displacements are herein called basic modal displacements (MBD). For each new design of the structure, the responses can be derived by well scaling each of the MBD along the time and amplitude and superposing them together using the corresponding modal matrices. To illustrate the efficiency of the method, an optimization problems is studied. The results show that the proposed approach is a suitable replacement for the conventional time history and spectrum analyses in such problems.

Keywords: basic modal displacements, earthquake, optimization, spectrum

Procedia PDF Downloads 361