Search results for: feature method

Authors: Majid Yazdandoust

Abstract:

This study, tries to suggest a design method based on displacement using finite difference numerical modeling in reinforcing soil retaining wall with steel strip. In this case, dynamic loading characteristics such as duration, frequency, peak ground acceleration, geometrical characteristics of reinforced soil structure and type of the site are considered to correct the pseudo static method and finally introduce the pseudo static coefficient as a function of seismic performance level and peak ground acceleration. For this purpose, the influence of dynamic loading characteristics, reinforcement length, height of reinforced system and type of the site are investigated on seismic behavior of reinforcing soil retaining wall with steel strip. Numerical results illustrate that the seismic response of this type of wall is highly dependent to cumulative absolute velocity, maximum acceleration, and height and reinforcement length so that the reinforcement length can be introduced as the main factor in shape of failure. Considering the loading parameters, mechanically stabilized earth wall parameters and type of the site showed that the used method in this study leads to most efficient designs in comparison with other methods which are generally suggested in cods that are usually based on limit-equilibrium concept. The outputs show the over-estimation of equilibrium design methods in comparison with proposed displacement based methods here.

Keywords: pseudo static coefficient, seismic performance design, numerical modeling, steel strip reinforcement, retaining walls, cumulative absolute velocity, failure shape

Procedia PDF Downloads 485

Authors: Woo-tai Jung, Jong-sup Park, Jae-yoon Kang, Moon-seoung Keum

Abstract:

CFRP (Carbon Fiber Reinforced Polymer) is mainly used as reinforcing material for degraded structures owing to its advantages including its non-corrodibility, high strength, and lightweight properties. Recently, dedicated studies focused not only on its simple bonding but also on its tensioning. The tension necessary for prestressing requires the anchoring of multi-CFRP tendons with high capacity and the surface treatment of the CFRP tendons may also constitute an important issue according to the type of anchor. The wedge type, swage type or bonded type anchor can be used to anchor the CFRP tendon. The bonded type anchor presents the disadvantage to lengthen the length of the anchor due to the low bond strength of the CFRP tendon without surface treatment. This study intends to overcome this drawback through the application of a method enlarging the bond area at the end of the CFRP tendon. This method enlarges the bond area by splitting the end of the CFRP tendon along its length and can be applied when CFRP is produced by pultrusion. The application of this method shows that the mono-CFRP tendon and 3-multi CFRP tendon secured the anchor performance corresponding to the tensile performance of the CFRP tendon and that the 7-multi tendon secured anchor performance corresponding to 90% of the tensile strength due to the occurrence of buckling in the steel tube anchorage.

Keywords: carbon fiber reinforced polymer (CFRP), tendon, anchor, tensile property, bond strength

Procedia PDF Downloads 247

Authors: Mahmoud S Gewaily, Atif Hasan, Mohamed Kassab, Ali A. Mansour

Abstract:

The current study was carried out on the nose of seventeenth healthy adult camels. Specimens were collected from slaughter houses then fixed, dissected and photographed. For ultra structural studies, fresh samples were fixed in different fixatives and prepared for examination by light, scanning and electron microscopes. Grossly, nose of the camel had narrow nostrils, slit like in outline. In the nasal cavity, the nasal vestibule was narrow and has scanty dorsal and lateral cartilaginous support. The Nasal conchae (dorsal, middle and ventral) enclosed the dorsal, middle conchal sinuses and no ventral conchal sinus; instead there was recess and bull a. The ethmoidal conchae (8 in number) were noticeably fewer than in the other domestic animals like ox and horse. The olfactory mucosa was restricted to a small area covering the caudal parts of the ethmoidal conchae. The lining epithelium of the nasal cavity changes gradually from stratified squamous epithelium in the nasal vestibule to pseudo stratified columnar ciliated in the respiratory region and finally, olfactory epithelium covering the caudal parts of the ethmoidal conchae. In the dromedary camel, a special feature was the presence of dense and relatively long hair covering the nostrils and the rostral part of the nasal vestibule. In conclusion, the anatomical features of the nose of the dromedary camel, especially in its rostral parts enable this animal to breathe properly in the sandy dry weather.

Keywords: camel nose, anatomy, dromedary camel, nasal vestibule

Procedia PDF Downloads 439

Authors: Ridzuan Ramli, Norhafzan Junadi, Mohammad D.H. Beg, Rosli M. Yunus

Abstract:

In this study, microcrystalline cellulose (MCC) was extracted from oil palm empty fruit bunch (EFB) cellulose which was earlier isolated from oil palm EFB fibre. In order to isolate the cellulose, the chlorination method was carried out. Then, the MCC was prepared by simultaneous ultrasonic and alkali treatment from the isolated α-cellulose. Based on mass balance calculation, the yields for MCC obtained from EFB was 44%. For fiber characterization, it is observed that the chemical composition of the hemicellulose and lignin for all samples decreased while composition for cellulose increased. The structural property of the MCC was studied by X-ray diffraction (XRD) method and the result shows that the MCC produced is a cellulose-I polymorph, with 73% crystallinity.

Keywords: oil palm empty fruit bunch, microcrystalline cellulose, ultrasonic, alkali treatment, x-ray diffraction

Procedia PDF Downloads 414

Authors: M. Marsadek, A. Mohamed

Abstract:

Power system security analysis is the most time demanding process due to large number of possible contingencies that need to be analyzed.  In a power system, any contingency resulting in security violation such as line overload or low voltage may occur for a number of reasons at any time.  To efficiently rank a contingency, both probability and the extent of security violation must be considered so as not to underestimate the risk associated with the contingency. This paper proposed a contingency ranking method that take into account the probabilistic nature of power system and the severity of contingency by using a newly developed method based on risk factor.  The proposed technique is implemented on IEEE 24-bus system.

Keywords: line overload, low voltage, probability, risk factor, severity

Procedia PDF Downloads 545

Authors: W. Mughees, M. Alahmad

Abstract:

Water is the most significant entity that controls local and global development. For the Gulf region, especially Saudi Arabia, with its limited potable water resources, the potential of the fresh water problem is highly considerable. In this research, the study involves the design and analysis of pinch-based water/wastewater networks. Multiple water/wastewater networks were developed using pinch analysis involving direct recycle/material recycle method. Property-integration technique was adopted to carry out direct recycle method. Particularly, a petroleum refinery was considered as a case study. In direct recycle methodology, minimum water discharge and minimum fresh water resource targets were estimated. Re-design (or retrofitting) of water allocation in the networks was undertaken. Chemical Oxygen Demand (COD) and hardness properties were taken as pollutants. This research was based on single and double contaminant approach for COD and hardness and the amount of fresh water was reduced from 340.0 m3/h to 149.0 m3/h (43.8%), 208.0 m3/h (61.18%) respectively. While regarding double contaminant approach, reduction in fresh water demand was 132.0 m3/h (38.8%). The required analysis was also carried out using mathematical programming technique. Operating software such as LINGO was used for these studies which have verified the graphical method results in a valuable and accurate way. Among the multiple water networks, the one possible water allocation network was developed based on mass exchange.

Keywords: minimization, water pinch, water management, pollution prevention

Procedia PDF Downloads 478

Authors: Hariti Rafika, Fekih Malika, Saighi Mohamed

Abstract:

Heat transfer by natural convection in storage tanks for LNG is extremely related to heat gains through the walls with thermal insulation is not perfectly efficient. In this paper, we present the study of natural convection in the unsteady regime for natural gas in aware phase using the fluent software. The gas is just on the surface of the liquid phase. The CFD numerical method used to solve the system of equations is based on the finite volume method. This numerical simulation allowed us to determine the temperature profiles, the stream function, the velocity vectors and the variation of the heat flux density in the vapor phase in the LNG storage tank volume. The results obtained for a general configuration, by numerical simulation were compared to those found in the literature.

Keywords: numerical simulation, natural convection, heat gains, storage tank, liquefied natural gas

Procedia PDF Downloads 437

Authors: Azam Najafkouchak, David Todem, Dorothy Pathak, Pramod Pathak, Joseph Gardiner

Abstract:

Propensity score (PS) methods have recently become the standard analysis tool for causal inference in observational studies where exposure is not randomly assigned. Thus, confounding can impact the estimation of treatment effect on the outcome. Due to the dangers of discretizing continuous variables, the focus of this paper will be on how the variation in cut-points or boundaries will affect the average treatment effect utilizing the stratification of the PS method. In this study, we will develop a new methodology to improve the efficiency of the PS analysis through stratification and simulation study. We will also explore the property of empirical distribution of average treatment effect theoretically, including asymptotic distribution, variance estimation and 95% confident Intervals.

Keywords: propensity score, stratification, emprical distribution, average treatment effect

Procedia PDF Downloads 97

Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride

Abstract:

In this work, we use machine learning and novel data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. To the best of our knowledge, this is the first work to apply modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.

Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning

Procedia PDF Downloads 134

Authors: Dalia Rimawi, Walid Salameh, Amal Al-Omari, Hadeel AbdelKhaleq

Abstract:

Predication of Survival time of patients with cancer, is a core factor that influences oncologist decisions in different aspects; such as offered treatment plans, patients’ quality of life and medications development. For a long time proportional hazards Cox regression (ph. Cox) was and still the most well-known statistical method to predict survival outcome. But due to the revolution of data sciences; new predication models were employed and proved to be more flexible and provided higher accuracy in that type of studies. Artificial neural network is one of those models that is suitable to handle time to event predication. In this study we aim to compare ph Cox regression with artificial neural network method according to data handling and Accuracy of each model.

Keywords: Cox regression, neural networks, survival, cancer.

Procedia PDF Downloads 200

Authors: Bilal Tebboub, AmelLabbani

Abstract:

This article introduces a compact sensor based on high-transmission, high-sensitivity two-dimensional photonic crystals. The photonic crystal consists of a square network of silicon rods in the air. The sensor is composed of two waveguide couplers and a microcavity designed for monitoring the percentage of hydrogen in the air and identifying gas types. Through the Finite-Difference Time-Domain (FDTD) method, we demonstrate that the sensor's resonance wavelength is contingent upon changes in the gas refractive index. We analyze transmission spectra, quality factors, and sensor sensitivity. The sensor exhibits a notable quality factor and a sensitivity value of 1374 nm/RIU. Notably, the sensor's compact structure occupies an area of 74.5 μm2, rendering it suitable for integrated optical circuits.

Keywords: 2-D photonic crystal, sensitivity, F.D.T.D method, label-free biosensing

Procedia PDF Downloads 92

Authors: Ayuko Itsuki, Sachiyo Aburatani

Abstract:

The seasonal (January, April, July and October) and monthly soil respiration rate and the monthly litter fall amounts were examined in the laurel-leaved (B_B-1) and Cryptomeria japonica (B_B-2 and PW) forests in the Kasugayama Hill Primeval Forest (Nara, Japan). The change of the seasonal soil respiration rate corresponded to that of the soil temperature. The soil respiration rate was higher in October when fresh organic matter was supplied in the forest floor than in April in spite of the same temperature. The seasonal soil respiration rate of B_B-1 was higher than that of B_B-2, which corresponded to more numbers of bacteria and fungi counted by the dilution plate method and by the direct count method by microscopy in B_B-1 than that of B_B-2. The seasonal soil respiration rate of B_B-2 was higher than that of PW, which corresponded to more microbial biomass by the direct count method by microscopy in B_B-2 than that of PW. The correlation coefficient with the seasonal soil respiration and the soil temperature was higher than that of the monthly soil respiration. The soil respiration carbon was more than the litter fall carbon. It was suggested that the soil respiration included in the carbon dioxide which was emitted by the plant root and soil animal, or that the litter fall supplied to the forest floor included in animal and plant litter.

Keywords: field soil respiration rate, forest soil, litter fall, mineralization rate

Procedia PDF Downloads 290

Authors: Saeid Shahraki, Mohammad Mahdi Kaekha

Abstract:

1030 steel, a kind of carbon steel used in homogenization, cold-forming, quenching, and tempering conditions, is generally utilized in small parts resisting medium stress, such as connection foundations, hydraulic cylinders, tiny gears, pins, clamps, automotive normal forging parts, camshafts, levers, pundits, and nuts. In this study, AC3 software was used to measure the effect of carbon and manganese percentage, dimensions and geometry of pieces, the type of the cooling fluid, temperature, and time on hardness and the content of 1030 steel phases. Next, the results are compared with the analytical values obtained from the Lumped Capacity Method.

Keywords: 1030Steel, AC3software, heat treatment, lumped capacity method

Procedia PDF Downloads 281

Authors: Kenichi Hirota, Jifeng Wang, Sadao Araki, Koji Endo, Hideki Yamamoto

Abstract:

Zirconium (Zr) has been used as a fuel cladding tube for nuclear reactors, because of the excellent corrosion resistance and the low adsorptive material for neutron. Generally speaking, the natural resource of Zr is often containing Hf that has similar properties. The content of Hf in the Zr resources is about 2~4 wt%. In the industrial use, the content of Hf in Zr resources should be lower than the 100 ppm. However, the separation of Zr and Hf is not so easy, because of similar chemical and physical properties such as melting point, boiling point and things. Solvent extraction method has been applied for the separation of Zr and Hf from Zr natural resources. This method can separate Hf with high efficiency (Hf < 100ppm), however, it needs much amount of organic solvents for solvent extraction and the cost of its disposal treatment is high. Therefore, we attached attention for the fractional crystallization. This separation method depends on the solubility difference of Zr and Hf in the solvent. In this work, hexafluorozirconate (hafnate) (K2Zr(Hf)F6) was used as model compound. Solubility of K2ZrF6 in water showed lower than that of K2HfF6. By repeating of this treatment, it is possible to purify Zr, practically. In this case, 16-18 times of recrystallization stages were needed for its high purification. The improvement of the crystallization process was carried out in this work. Water, hydrofluoric acid (HF) and hydrofluoric acid (HF) +hydrochloric acid (HCl) mixture were chosen as solvent for dissolution of Zr and Hf. In the experiment, 10g of K2ZrF6 was added to each solvent of 100mL. Each solution was heated for 1 hour at 353K. After 1h of this operation, they were cooled down till 293K, and were held for 5 hours at 273K. Concentration of Zr or Hf was measured using ICP analysis. It was found that Hf was separated from Zr-Hf mixed compound with high efficiency, when HF-HCl solution was used for solvent of crystallization. From the comparison of the particle size of each crystal by SEM, it was confirmed that the particle diameter of the crystal showed smaller size with decreasing of Hf content. This paper concerned with purification of Zr from Zr-Hf mixture using crystallization method.

Keywords: crystallization, zirconium, hafnium, separation

Procedia PDF Downloads 438

Authors: Slimane Ouhmad, Abdellah Halimi

Abstract:

In this work, we have applied neural networks method MLP type to a database from an array of six sensors for the detection of three toxic gases. As the choice of the number of hidden layers and the weight values has a great influence on the convergence of the learning algorithm, we proposed, in this article, a mathematical formulation to determine the optimal number of hidden layers and good weight values based on the method of back propagation of errors. The results of this modeling have improved discrimination of these gases on the one hand, and optimize the computation time on the other hand, the comparison to other results achieved in this case.

Keywords: MLP Neural Network, back-propagation, number of neurons in the hidden layer, identification, computing time

Procedia PDF Downloads 347

Authors: Subrato Saha, Yun-Hyun Cho

Abstract:

This paper presents the design process of a high performance 3-phase 3.7 kW 2-pole line start permanent magnet synchronous motor for pumping system. A method was proposed to study the starting torque characteristics considering line start with high inertia load. A d-q model including cage was built to study the synchronization capability. Time-stepping finite element method analysis was utilized to accurately predict the dynamic and transient performance, efficiency, starting current, speed curve and, etc. Considering the load torque of pumps during starting stage, the rotor bar was designed with minimum demagnetization of permanent magnet caused by huge starting current.

Keywords: LSPM, starting analysis, demagnetization, FEA, pumping system

Procedia PDF Downloads 471

Authors: Katsumi Hirata

Abstract:

Certain systems can function well only if they recognize the sound environment as humans do. In this research, we focus on sound classification by adopting a convolutional neural network and aim to develop a method that automatically classifies various environmental sounds. Although the neural network is a powerful technique, the performance depends on the type of input data. Therefore, we propose an approach via a slice bispectrogram, which is a third-order spectrogram and is a slice version of the amplitude for the short-time bispectrum. This paper explains the slice bispectrogram and discusses the effectiveness of the derived method by evaluating the experimental results using the ESC‑50 sound dataset. As a result, the proposed scheme gives high accuracy and stability. Furthermore, some relationship between the accuracy and non-Gaussianity of sound signals was confirmed.

Keywords: environmental sound, bispectrum, spectrogram, slice bispectrogram, convolutional neural network

Procedia PDF Downloads 126

Authors: Mohamad Mohsen Homayouni, Niloofar Taghipour, Ahmad Reza Memar, Niloofar Khalaji, Hamed Kiani, Seyyed Javad Seyyed Tabaei

Abstract:

Background and Objective: Cryptosporidium is a coccidian protozoan parasite; its oocysts in surface water are a global health problem. Due to the low number of parasites in the water resources and the lack of laboratory culture, rapid and sensitive method for detection of the organism in the water resources is necessarily required. We applied modified acid-fast staining and PCR for the detection of the Cryptosporidium spp. and analysed the genotypes in 55 samples collected from surface water. Methods: Over a period of nine months, 55 surface water samples were collected from the five rivers in Tehran, Iran. The samples were filtered by using cellulose acetate membrane filters. By acid fast method, initial identification of Cryptosporidium oocyst were carried out on surface water samples. Then, nested PCR assay was designed for the specific amplification and analysed the genotypes. Results: Modified Ziehl-Neelsen method revealed 5–20 Cryptosporidium oocysts detected per 10 Liter. Five out of the 55 (9.09%) surface water samples were found positive for Cryptosporidium spp. by Ziehl-Neelsen test and seven (12.7%) were found positive by nested PCR. The staining results were consistent with PCR. Seven Cryptosporidium PCR products were successfully sequenced and five gp60 subtypes were detected. Our finding of gp60 gene revealed that all of the positive isolates were Cryptosporidium parvum and belonged to subtype families IIa and IId. Conclusion: Our investigations were showed that collection of water samples were contaminated by Cryptosporidium, with potential hazards for the significant health problem. This study provides the first report on detection and genotyping of Cryptosporidium species from surface water samples in Iran, and its result confirmed the low clinical incidence of this parasite on the community.

Keywords: Cryptosporidium spp., membrane filtration, subtype, surface water, Iran

Procedia PDF Downloads 416

Authors: Kyoung-Jin Joo, In-Gun Kim, Hyun-Seok Hong, Dong-Woo Kang, Ju Lee

Abstract:

Recently, the permanent magnet-assisted synchronous reluctance motor (PMa-SynRM) that can be substituted for the induction motor has been studying because of the needs of the development of the premium high efficiency motor for the minimum energy performance standard (MEPS). PMa-SynRM is required to the speed and position information for motor speed and torque controls. However, to apply the sensors has many problems that are sensor mounting space shortage and additional cost, etc. Therefore, in this paper, speed-sensorless control based on model reference adaptive system (MRAS) is introduced to eliminate the sensor. The sensorless method is constructed in a reference model as standard and an adaptive model as the state observer. The proposed algorithm is verified by the simulation.

Keywords: PMa-SynRM, sensorless control, robust estimation, MRAS method

Procedia PDF Downloads 404

Authors: E. H. N. Gashti, J. Razzaghi, K. Kujala

Abstract:

In general, codes and regulations consider seismic loads only for completed structures of the bridges while, evaluation of incomplete structure of bridges, especially those constructed by free cantilever method, under these loads is also of great importance. Hence, this research tried to study the behavior of incomplete structure of common bridge type (box girder bridge), in construction phase under vertical seismic loads. Subsequently, the paper provided suitable guidelines and solutions to withstand this destructive phenomena. Research results proved that use of preventive methods can significantly reduce the stresses resulted from vertical seismic loads in box cross sections to an acceptable range recommended by design codes.

Keywords: box girder bridges, prestress loads, free cantilever method, seismic loads, construction phase

Procedia PDF Downloads 345

Authors: Yang Zhong, Meijie Xu

Abstract:

The explicit solutions for the natural frequencies and mode shapes of the orthotropic rectangular plate with four clamped edges are presented by the double finite cosine integral transform method. In the analysis procedure, the classical orthotropic rectangular thin plate is considered. Because only are the basic dynamic elasticity equations of the orthotropic thin plate adopted, it is not need prior to select the deformation function arbitrarily. Therefore, the solution developed by this paper is reasonable and theoretical. Finally, an illustrative example is given and the results are compared with those reported earlier. This method is found to be easier and effective. The results show reasonable agreement with other available results, but with a simpler and practical approach.

Keywords: rectangular orthotropic plate, four clamped edges, natural frequencies and mode shapes, finite integral transform

Procedia PDF Downloads 577

Authors: Zhemi Xu, Dewei Chu, Sean Li

Abstract:

Well self-assembled pure and Mn-doped SnO2 nanocubes were synthesized by interface thermodynamic method, which is ideal for highly homogeneous large scale thin film deposition on flexible substrates for various electric devices. Mn-doped SnO2 shows very good resistive switching with high On/Off ratio (over 103), endurance and retention characteristics. More important, the resistive state can be tuned by multi-layer fabrication by alternate pure SnO2 and Mn-doped SnO2 nanocube layer, which improved the memory capacity of resistive switching effectively. Thus, such a method provides transparent, multi-level resistive switching for next generation non-volatile memory applications.

Keywords: metal oxides, self-assembly nanoparticles, multi-level resistive switching, multi-layer thin film

Procedia PDF Downloads 345

Authors: Pablo Oteiza, Ricardo Alvarez, Mehrdad Pirnia, Fuat Can

Abstract:

To effectively combat climate change, many countries around the world have committed to a decarbonisation of their electricity, along with promoting a large-scale integration of renewable energy sources (RES). While this trend represents a unique opportunity to effectively combat climate change, achieving a sound and cost-efficient energy transition towards low-carbon power systems poses significant challenges for the multi-year Transmission Network Expansion Planning (TNEP) problem. The objective of the multi-year TNEP is to determine the necessary network infrastructure to supply the projected demand in a cost-efficient way, considering the evolution of the new generation mix, including the integration of RES. The rapid integration of large-scale RES increases the variability and uncertainty in the power system operation, which in turn increases short-term flexibility requirements. To meet these requirements, flexible generating technologies such as energy storage systems must be considered within the TNEP as well, along with proper models for capturing the operational challenges of future power systems. As a consequence, TNEP formulations are becoming more complex and difficult to solve, especially for its application in realistic-sized power system models. To meet these challenges, there is an increasing need for developing efficient algorithms capable of solving the TNEP problem with reasonable computational time and resources. In this regard, a promising research area is the use of artificial intelligence (AI) techniques for solving large-scale mixed-integer optimization problems, such as the TNEP. In particular, the use of AI along with mathematical optimization strategies based on decomposition has shown great potential. In this context, this paper presents an efficient algorithm for solving the multi-year TNEP problem. The algorithm combines AI techniques with Column Generation, a traditional decomposition-based mathematical optimization method. One of the challenges of using Column Generation for solving the TNEP problem is that the subproblems are of mixed-integer nature, and therefore solving them requires significant amounts of time and resources. Hence, in this proposal we solve a linearly relaxed version of the subproblems, and trained a binary classifier that determines the value of the binary variables, based on the results obtained from the linearized version. A key feature of the proposal is that we integrate the binary classifier into the optimization algorithm in such a way that the optimality of the solution can be guaranteed. The results of a study case based on the HRP 38-bus test system shows that the binary classifier has an accuracy above 97% for estimating the value of the binary variables. Since the linearly relaxed version of the subproblems can be solved with significantly less time than the integer programming counterpart, the integration of the binary classifier into the Column Generation algorithm allowed us to reduce the computational time required for solving the problem by 50%. The final version of this paper will contain a detailed description of the proposed algorithm, the AI-based binary classifier technique and its integration into the CG algorithm. To demonstrate the capabilities of the proposal, we evaluate the algorithm in case studies with different scenarios, as well as in other power system models.

Keywords: integer optimization, machine learning, mathematical decomposition, transmission planning

Procedia PDF Downloads 85

Authors: S. Bennoud, M. Zergoug

Abstract:

The numerical simulation of electromagnetic interactions is still a challenging problem, especially in problems that result in fully three dimensional mathematical models. The goal of this work is to use mathematical modeling to characterize the reliability and capacity of eddy current technique to detect and characterize defects embedded in aeronautical in-service pieces. The finite element method is used for describing the eddy current technique in a mathematical model by the prediction of the eddy current interaction with defects. However, this model is an approximation of the full Maxwell equations. In this study, the analysis of the problem is based on a three dimensional finite element model that computes directly the electromagnetic field distortions due to defects.

Keywords: eddy current, finite element method, non destructive testing, numerical simulations

Procedia PDF Downloads 443

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 278

Authors: Azam Mohammadbagheri, Bahram Fathi

Abstract:

DEA has become a very popular method of performance measure, but it still suffers from some shortcomings. One of these shortcomings is the issue of having multiple optimal solutions to weights for efficient DMUs. The cross efficiency evaluation as an extension of DEA is proposed to avoid this problem. Lam (2010) is also proposed a mixed-integer linear programming formulation based on linear discriminate analysis and super efficiency method (MILP model) to avoid having multiple optimal solutions to weights. In this study, we modified MILP model to determine more suitable weight sets and also evaluate the energy efficiency of MENA countries as an application of the proposed model.

Keywords: data envelopment analysis, discriminate analysis, cross efficiency, MILP model

Procedia PDF Downloads 687

Authors: Mostafa Mjahed

Abstract:

Tilt Rotor UAVs (Unmanned Aerial Vehicles) are naturally unstable and difficult to maneuver. The purpose of this paper is to design controllers for the stabilization and trajectory tracking of this type of UAV. To this end, artificial intelligence methods have been exploited. First, the dynamics of this UAV was modeled using the Lagrange-Euler method. The conventional method based on Proportional, Integral and Derivative (PID) control was applied by decoupling the different flight modes. To improve stability and trajectory tracking of the Tilt Rotor, the fuzzy approach and the technique of multilayer neural networks (NN) has been used. Thus, Fuzzy Proportional Integral and Derivative (FPID) and Neural Network-based Proportional Integral and Derivative controllers (NNPID) have been developed. The meta-heuristic approach based on Particle Swarm Optimization (PSO) method allowed adjusting the setting parameters of NNPID controller, giving us an improved NNPID-PSO controller. Simulation results under the Matlab environment show the efficiency of the approaches adopted. Besides, the Tilt Rotor UAV has become stable and follows different types of trajectories with acceptable precision. The Fuzzy, NN and NN-PSO-based approaches demonstrated their robustness because the presence of the disturbances did not alter the stability or the trajectory tracking of the Tilt Rotor UAV.

Keywords: neural network, fuzzy logic, PSO, PID, trajectory tracking, tilt-rotor UAV

Procedia PDF Downloads 120

Authors: Christine Böckmann, Julia Rosemann

Abstract:

We present an inversion algorithm that is used in the European Aerosol Lidar Network for the inversion of data collected with multi-wavelength Raman lidar. These instruments measure backscatter coefficients at 355, 532, and 1064 nm, and extinction coefficients at 355 and 532 nm. The algorithm is based on manually controlled inversion of optical data which allows for detailed sensitivity studies and thus provides us with comparably high quality of the derived data products. The algorithm allows us to derive particle effective radius, volume, surface-area concentration with comparably high confidence. The retrieval of the real and imaginary parts of the complex refractive index still is a challenge in view of the accuracy required for these parameters in climate change studies in which light-absorption needs to be known with high accuracy. Single-scattering albedo (SSA) can be computed from the retrieve microphysical parameters and allows us to categorize aerosols into high and low absorbing aerosols. From mathematical point of view the algorithm is based on the concept of using truncated singular value decomposition as regularization method. This method was adapted to work for the retrieval of the particle size distribution function (PSD) and is called hybrid regularization technique since it is using a triple of regularization parameters. The inversion of an ill-posed problem, such as the retrieval of the PSD, is always a challenging task because very small measurement errors will be amplified most often hugely during the solution process unless an appropriate regularization method is used. Even using a regularization method is difficult since appropriate regularization parameters have to be determined. Therefore, in a next stage of our work we decided to use two regularization techniques in parallel for comparison purpose. The second method is an iterative regularization method based on Pade iteration. Here, the number of iteration steps serves as the regularization parameter. We successfully developed a semi-automated software for spherical particles which is able to run even on a parallel processor machine. From a mathematical point of view, it is also very important (as selection criteria for an appropriate regularization method) to investigate the degree of ill-posedness of the problem which we found is a moderate ill-posedness. We computed the optical data from mono-modal logarithmic PSD and investigated particles of spherical shape in our simulations. We considered particle radii as large as 6 nm which does not only cover the size range of particles in the fine-mode fraction of naturally occurring PSD but also covers a part of the coarse-mode fraction of PSD. We considered errors of 15% in the simulation studies. For the SSA, 100% of all cases achieve relative errors below 12%. In more detail, 87% of all cases for 355 nm and 88% of all cases for 532 nm are well below 6%. With respect to the absolute error for non- and weak-absorbing particles with real parts 1.5 and 1.6 in all modes the accuracy limit +/- 0.03 is achieved. In sum, 70% of all cases stay below +/-0.03 which is sufficient for climate change studies.

Keywords: aerosol particles, inverse problem, microphysical particle properties, regularization

Procedia PDF Downloads 343

Authors: Ya Lv

Abstract:

This article presents the application of the semi-analytic method (SAM) in the thermal management solution (TMS) of the energy storage system (ESS). The TMS studied in this work is fluid cooling. In fluid cooling, both effective heat conduction and heat convection are indispensable due to the heat transfer from solid to fluid. Correspondingly, an efficient TMS requires a design investigation of the following parameters: fluid inlet temperature, ESS initial temperature, fluid flow rate, working c rate, continuous working time, and materials properties. Their variation induces a change of thermal performance in the battery module, which is usually evaluated by numerical simulation. Compared to complicated computation resources and long computation time in simulation, the SAM is developed in this article to predict the thermal influence within a few seconds. In SAM, a fast prediction model is reckoned by combining numerical simulation with theoretical/empirical equations. The SAM can explore the thermal effect of boundary parameters in both steady-state and transient heat transfer scenarios within a short time. Therefore, the SAM developed in this work can simplify the design cycle of TMS and inspire more possibilities in TMS design.

Keywords: semi-analytic method, fast prediction model, thermal influence of boundary parameters, energy storage system

Procedia PDF Downloads 154

Authors: RyongJin Ri, SongChol Kim, SungIl Jon, KyongIl Ji

Abstract:

: In this paper, an improved algorithm is proposed to eliminate the distortion of terrain relief when generating DEMs from digitized contour lines in the area bounded by inflectional contour lines such as narrow and long mountain ridges or valleys. To this end, mountain ridge lines (valley lines) are extracted from the area, and the steepest slope segment is detected based on ridge or valley lines. After detecting the steepest slope segment, the elevation of the grid points is interpolated on the profile section using the cubic Hermit function. The experiment shows that the accuracy of the DEM of the terrain-distortionable region generated by the proposed method is improved significantly.

Keywords: DEM, contour lines, ridge line, steepest slope segment

Procedia PDF Downloads 8