Search results for: social reinforcement

Authors: Jaime R. Silva, Gabriel E. Reyes, Marianne Krause

Abstract:

Background: The two-polarity model of the depressive personality argues that experience is organized around two axes: interpersonal relatedness and self-definition. Differential emphasis on one of these poles defines three types of depressive experience: Anaclitic, Introjective or Mixed pattern. On the one hand, Anaclitic pattern has been conceptually related with exaggerated biological stress sensitivity. On the other hand, the Introjective pattern was linked with anhedonic symptomatology. The general aim of the study was to find empirical support for this relationship. Methods: 101 non-clinical individuals participated in two experimental sessions. During the first session, the biological stress reactivity (cortisol concentration in saliva) and the subjective stress perceived (self-reported) during the Trier Social Stress Test (TSST), were investigated. In the second session, a visual discrimination task with a specific reward system, to study the reinforcement sensitivity (anhedonia), was performed. Results: Results evidenced that participants with Introjective depressive symptoms showed a higher interpersonal sensitivity and a diminished sensitivity to reinforcement. In addition, results also indicated that such a group has a poor psychological detection of its exacerbated reactivity to stress, which is the opposite pattern evidenced amongst the Anaclitic group. Conclusions: In perspective, these results empirically support the two-polarity of the depressive personality model. Clinical implications are discussed.

Keywords: depression, interpersonal stress, personality, trier social stress test

Procedia PDF Downloads 245

Authors: Olaf Visker, Arnout De Vries, Lambert Schomaker

Abstract:

Predictive policing refers to the usage of analytical techniques to identify potential criminal activity. It has been widely implemented by various police departments. Being a relatively new area of research, there are, to the author’s knowledge, no absolute tried, and true methods and they still exhibit a variety of potential problems. One of those problems is closely related to the lack of understanding of how acting on these prediction influence crime itself. The goal of law enforcement is ultimately crime reduction. As such, a policy needs to be established that best facilitates this goal. This research aims to find such a policy by using adversarial agent-based modeling in combination with modern reinforcement learning techniques. It is presented here that a baseline model for both law enforcement and criminal agents and compare their performance to their respective reinforcement models. The experiments show that our smart law enforcement model is capable of reducing crime by making more deliberate choices regarding the locations of potential criminal activity. Furthermore, it is shown that the smart criminal model presents behavior consistent with popular crime theories and outperforms the baseline model in terms of crimes committed and time to capture. It does, however, still suffer from the difficulties of capturing long term rewards and learning how to handle multiple opposing goals.

Keywords: adversarial, agent based modelling, predictive policing, reinforcement learning

Procedia PDF Downloads 145

Authors: Harshit Agrawal, Salman Muhammad

Abstract:

Degradation to reinforced concrete (RC), primarily due to corrosion of embedded reinforcement, has been a major cause of concern worldwide. Among several ways to control corrosion, the use of coated reinforcement has gained significant interest in field applications. However, the choice of proper coating material and the effect of damage over coating are yet to be addressed for effective application of coated reinforcements. The present study aims to investigate and compare the performance of three different types of coated reinforcements —Fusion-Bonded Epoxy Coating (FBEC), Cement Polymer Composite Coating (CPCC), and Dual Zinc-Epoxy Coating (DZEC) —in concrete structures. The aim is to assess their corrosion resistance, durability, and overall effectiveness as coated reinforcement materials both in undamaged and simulated damaged conditions. Through accelerated corrosion tests, electrochemical analysis, and exposure to aggressive marine environments, the study evaluates the long-term performance of each coating system. This research serves as a crucial guide for engineers and construction professionals in selecting the most suitable corrosion protection for reinforced concrete, thereby enhancing the durability and sustainability of infrastructure.

Keywords: corrosion, reinforced concrete, coated reinforcement, seawater exposure, electrochemical analysis, service life, corrosion prevention

Procedia PDF Downloads 73

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 228

Authors: Arun Sanjel, Greg Speegle

Abstract:

Every second, massive amounts of data are generated, and Data Intensive Scalable Computing (DISC) frameworks have evolved into effective tools for analyzing such massive amounts of data. Since the underlying architecture of these distributed computing platforms is often new to users, building a DISC application can often be time-consuming and prone to errors. The automated conversion of a sequential program to a DISC program will consequently significantly improve productivity. However, synthesizing a user’s intended program from an input specification is complex, with several important applications, such as distributed program synthesizing and code refactoring. Existing works such as Tyro and Casper rely entirely on deductive synthesis techniques or similar program synthesis approaches. Our approach is to develop a data-driven synthesis technique to identify sequential components and translate them to equivalent distributed operations. We emphasize using reinforcement learning and unit testing as feedback mechanisms to achieve our objectives.

Keywords: program synthesis, distributed computing, reinforcement learning, unit testing, DISC

Procedia PDF Downloads 93

Authors: Vijaya Yuvaram Singh V M, Kameshwar Rao J V

Abstract:

The challenge with development of neural network based methods for medical is the availability of data. Anatomical landmark detection in the medical domain is a process to find points on the x-ray scan report of the patient. Most of the time this task is done manually by trained professionals as it requires precision and domain knowledge. Traditionally object detection based methods are used for landmark detection. Here, we utilize reinforcement learning and query based method to train a single agent capable of detecting multiple landmarks. A deep Q network agent is trained to detect single and multiple landmarks present on hip and shoulder from x-ray scan of a patient. Here a single agent is trained to find multiple landmark making it superior to having individual agents per landmark. For the initial study, five images of different patients are used as the environment and tested the agents performance on two unseen images.

Keywords: reinforcement learning, medical landmark detection, multi target detection, deep neural network

Procedia PDF Downloads 137

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 58

Authors: Mostafa Amirjan

Abstract:

In the present study, the properties of Al-Al2O3 nanocomposite hollow sphere structures were investigated. For this reason, the Al-based nanocomposite hollow spheres with different amounts of nano alumina reinforcement (0-10wt %) and different ratio of thickness to diameter (t/D: 0.06-0.3) were prepared via a powder metallurgy method. Then, the effect of mentioned parameters was studied on physical and quasi static mechanical properties of their related prepared structures (open/closed cell) such as density, hardness, strength and energy absorption. It was found that as the t/D ratio increases the relative density, compressive strength and energy absorption increase. The highest values of strength and energy absorption were obtained from the specimen with 5 wt. % of nanoparticle reinforcement, t/D of 0.3 (t=1 mm, D=400µm) as 22.88 MPa and 13.24 MJ/m3, respectively. The moderate specific strength of prepared composites in the present study showed the good consistency with the properties of others low carbon steel composite with similar structure.

Keywords: hollow sphere structure foam, nanocomposite, thickness and diameter (t/D ), powder metallurgy

Procedia PDF Downloads 447

Authors: Farzaneh Sarbandi Farahani

Abstract:

Drought and decrease in the level of lakes in recent years due to global warming and excessive use of water resources feeding lakes are of great importance, and this research has provided a structure to investigate this issue. First, the information required for simulating lake drought is provided with strong references and necessary assumptions. Entity-Component-System (ECS) structure has been used for simulation, which can consider assumptions flexibly in simulation. Three major users (i.e., Industry, agriculture, and Domestic users) consume water from groundwater and surface water (i.e., streams, rivers and lakes). Lake Mead has been considered for simulation, and the information necessary to investigate its drought has also been provided. The results are presented in the form of a scenario-based design and optimal strategy selection. For optimal strategy selection, a deep reinforcement algorithm is developed to select the best set of strategies among all possible projects. These results can provide a better view of how to plan to prevent lake drought.

Keywords: drought simulation, Mead lake, entity component system programming, deep reinforcement learning

Procedia PDF Downloads 82

Authors: Reginald Umunakwe, Obinna Chibuzor Okoye, Uzoma Samuel Nwigwe, Damilare John Olaleye, Akinlabi Oyetunji

Abstract:

The potential for the development of PPS-AlMMCs as light weight material for industrial applications was investigated. Periwinkle shells were milled and the density of the particles determined. Particulate periwinkle shell of particle size 75µm was used to reinforce aluminium 6063 alloy at 10wt% filler loading using two-step stir casting technique. The composite materials were stirred for five minutes in a semi-solid state and the stirring time varied as 3, 6 and 9 minutes at above the liquidus temperature. A specimen was also produced with pre-heated filler. The effect of variation in stirring time and reinforcement pre-heating on the porosity of the composite materials was investigated. The results of the analysis show that a composition of reinforcement pre-heating and stirring for 3 minutes produced a composite material with the lowest porosity of 1.05%.

Keywords: composites, periwinkle shell, two-step casting, porosity

Procedia PDF Downloads 346

Authors: Akhila Palat, B. Umashankar

Abstract:

Back-to-back Mechanically Stabilized Earth (MSE) walls are cost-effective soil-retaining structures that can tolerate large settlements compared to conventional gravity retaining walls. They are also an economical way to meet everyday earth retention needs for highway and bridge grade separations, railroads, commercial and residential developments. But, existing design guidelines (FHWA/BS/ IS codes) do not provide a mechanistic approach for the design of back-to-back reinforced retaining walls. The settlement analysis of such structures is limited in the literature. A better understanding of the deformations of this wall system requires an analytical tool that incorporates the properties of backfill material, foundation soil, and geosynthetic reinforcement, and account for the soil–structure interactions in a realistic manner. This study was conducted to investigate the effect of reinforced back-to-back MSE walls on wall settlements and facing deformations. Back-to-back reinforced retaining walls were modeled and compared using commercially available finite difference package FLAC 2D. Parametric studies were carried out for various angles of shearing resistance of backfill material and foundation soil, and the axial stiffness of the reinforcement. A 6m-high wall was modeled, and the facing panels were taken as full-length panels with nominal thickness. Reinforcement was modeled as cable elements (two-dimensional structural elements). Interfaces were considered between soil and wall, and soil and reinforcement.

Keywords: back-to-back walls, numerical modeling, reinforced wall, settlement

Procedia PDF Downloads 299

Authors: Anjana R. Menon, Anjana Bhasi

Abstract:

Development of highways and railways play crucial role in a nation’s economic growth. While rigid concrete pavements are durable with high load bearing characteristics, growing economies mostly rely on flexible pavements which are easier in construction and more economical. The strength of flexible pavement is based on the strength of subgrade and load distribution characteristics of intermediate granular layers. In this scenario, to simultaneously meet economy and strength criteria, it is imperative to strengthen and stabilize the load transferring layers, namely subbase and base. Geosynthetic reinforcement in planar and cellular forms have been proven effective in improving soil stiffness and providing a stable load transfer platform. Studies have proven the relative superiority of cellular form-geocells over planar geosynthetic forms like geogrid, owing to the additional confinement of infill material and pocket effect arising from vertical deformation. Hence, the present study investigates the efficiency of geocells over single/multiple layer geogrid reinforcements by a series of three-dimensional model analyses of a flexible pavement section under a standard repetitive wheel load. The stress transfer mechanism and deformation profiles under various reinforcement configurations are also studied. Geocell reinforcement is observed to take up a higher proportion of stress caused by the traffic loads compared to single and double-layer geogrid reinforcements. The efficiency of single geogrid reinforcement reduces with an increase in embedment depth. The contribution of lower geogrid is insignificant in the case of the double-geogrid reinforced system.

Keywords: Geocell, Geogrid, Flexible Pavement, Repetitive Wheel Load, Numerical Analysis

Procedia PDF Downloads 71

Authors: C. Sánchez de Rojas Candela, A. Riquelme, P. Rodrigo, M. D. Escalera-Rodríguez, B. Torres, J. Rams

Abstract:

Selective laser melting is one of the most commonly used AM techniques. In it, a thin layer of metallic powder is deposited, and a laser is used to melt selected zones. The accumulation of layers, each one molten in the preselected zones, gives rise to the formation of a 3D sample with a nearly arbitrary design. To ensure that the properties of the final parts match those of the powder, all the process is carried out in an inert atmosphere, preferentially Ar, although this gas could be substituted. Ti6Al4V alloy is widely used in multiple industrial applications such as aerospace, maritime transport and biomedical, due to its properties. However, due to the demanding requirements of these applications, greater hardness and wear resistance are necessary, together with a better machining capacity, which currently limits its commercialization. To improve these properties, in this study, Selective Laser Melting (SLM) is used to manufacture Ti/TiN metal matrix composites with in-situ and ex-situ titanium nitride reinforcement where the scanning speed is modified (from 28.5 up to 65 mm/s) to study the influence of the processing parameters in SLM. A one-step method of nitriding the Ti6Al4V alloy is carried out to create in-situ TiN reinforcement in a reactive atmosphere and it is compared with ex-situ composites manufactured by previous mixture of both the titanium alloy powder and the ceramic reinforcement particles. The microstructure and mechanical properties of the different Ti/TiN composite materials have been analyzed. As a result, the existence of a similar matrix has been confirmed in in-situ and ex-situ fabrications and the growth mechanisms of the nitrides have been studied. An increase in the mechanical properties with respect to the initial alloy has been observed in both cases and related to changes in their microstructure. Specifically, a greater improvement (around 30.65%) has been identified in those manufactured by the in-situ method at low speeds although other properties such as porosity must be improved for their future industrial applicability.

Keywords: in-situ reinforcement, nitriding reaction, selective laser melting, titanium nitride

Procedia PDF Downloads 75

Authors: O. Vlcek

Abstract:

The paper deals with current issues in research of advanced methods to increase reliability of traditional timber structural elements. It analyses the issue of strengthening of bent timber beams, such as ceiling beams in old (historical) buildings with additional concrete slab in combination with externally bonded fibre - reinforced polymer. The paper describes experimental testing of composite timber-concrete beam with FRP reinforcement and compares results with FEM analysis.

Keywords: timber-concrete composite, strengthening, fibre-reinforced polymer, experimental analysis

Procedia PDF Downloads 468

Authors: Hiba S. Ahmed, Abbas A. Allawi, Riyadh A. Hindi

Abstract:

Pultruded materials made of fiber-reinforced polymer (FRP) come in a broad range of shapes, such as bars, I-sections, C-sections, and other structural sections. These FRP materials are starting to compete with steel as structural materials because of their great resistance, low self-weight, and cheap maintenance costs-especially in corrosive conditions. This study aimed to evaluate the effectiveness of Glass Fiber Reinforced Polymer (GFRP) of the hybrid columns built by combining (GFRP) profiles with concrete columns because of their low cost and high structural efficiency. To achieve the aims of this study, nine circular columns with a diameter of (150 mm) and a height of (1000mm) were cast using normal concrete with compression strength equal to (35 MPa). The research involved three different types of reinforcement: hybrid circular columns type (IG) with GFRP I-section and 1% of the reinforcement ratio of steel bars, hybrid circular columns type (IS) with steel I-section and 1% of the reinforcement ratio of steel bars, (where the cross-section area of I-section for GFRP and steel was the same), compared with reference column (R) without I-section. To investigate the ultimate capacity, axial and lateral deformation, strain in longitudinal and transverse reinforcement, and failure mode of the circular column under different loading conditions (concentric and eccentric) with eccentricities of 25 mm and 50 mm, respectively. In the second part, an analytical finite element model will be performed using ABAQUS software to validate the experimental results.

Keywords: composite, columns, reinforced concrete, GFRP, axial load

Procedia PDF Downloads 47

Authors: Martin Tazky, Rudolf Hela, Lucia Osuska, Petr Novosad

Abstract:

Concrete’s volumetric changes are natural process caused by silicate minerals’ hydration. These changes can lead to cracking and subsequent destruction of cementitious material’s matrix. In most cases, cracks can be assessed as a negative effect of hydration, and in all cases, they lead to an acceleration of degradation processes. Preventing the formation of these cracks is, therefore, the main effort. Once of the possibility how to eliminate this natural concrete shrinkage process is by using different types of dispersed reinforcement. For this application of concrete shrinking, steel and polymer reinforcement are preferably used. Despite ordinarily used reinforcement in concrete to eliminate shrinkage it is possible to look at this specific problematic from the beginning by itself concrete mix composition. There are many secondary raw materials, which are helpful in reduction of hydration heat and also with shrinkage of concrete during curing. The new science shows the possibilities of shrinkage reduction also by the controlled formation of hydration products, which could act by itself morphology as a traditionally used dispersed reinforcement. This contribution deals with the possibility of controlled formation of mono- and tri-sulfate which are considered like degradation minerals. Mono- and tri- sulfate's controlled formation in a cementitious composite can be classified as a self-healing ability. Its crystal’s growth acts directly against the shrinking tension – this reduces the risk of cracks development. Controlled formation means that these crystals start to grow in the fresh state of the material (e.g. concrete) but stop right before it could cause any damage to the hardened material. Waste materials with the suitable chemical composition are very attractive precursors because of their added value in the form of landscape pollution’s reduction and, of course, low cost. In this experiment, the possibilities of using the fly ash from fluidized bed combustion as a mono- and tri-sulphate formation additive were investigated. The experiment itself was conducted on cement paste and concrete and specimens were subjected to a thorough analysis of physicomechanical properties as well as microstructure from the moment of mixing up to 180 days. In cement composites, were monitored the process of hydration and shrinkage. In a mixture with the used admixture of fluidized bed combustion fly ash, possible failures were specified by electronic microscopy and dynamic modulus of elasticity. The results of experiments show the possibility of shrinkage concrete reduction without using traditionally dispersed reinforcement.

Keywords: shrinkage, monosulphates, trisulphates, self-healing, fluidized fly ash

Procedia PDF Downloads 180

Authors: William Li

Abstract:

Lane-change path planning is a crucial and yet complex task in autonomous driving. The traditional path planning approach based on a system of carefully-crafted rules to cover various driving scenarios becomes unwieldy as more and more rules are added to deal with exceptions and corner cases. This paper proposes to divide the entire path planning to two stages. In the first stage the ego vehicle travels longitudinally in the source lane to reach a safe state. In the second stage the ego vehicle makes lateral lane-change maneuver to the target lane. The paper derives the safe state conditions based on lateral lane-change maneuver calculation to ensure collision free in the second stage. To determine the acceleration sequence that minimizes the time to reach a safe state in the first stage, the paper proposes three schemes, namely, kinetic model based optimization, deep reinforcement learning, and 5G vehicle-to-vehicle (V2V) communications. The paper investigates these schemes via simulation. The model-based optimization is sensitive to the model assumptions. The deep reinforcement learning is more flexible in handling scenarios beyond the model assumed by the optimization. The 5G V2V eliminates uncertainty in predicting future behaviors of surrounding vehicles by sharing driving intents and enabling cooperative driving.

Keywords: lane change, path planning, autonomous driving, deep reinforcement learning, 5G, V2V communications, connected vehicles

Procedia PDF Downloads 229

Authors: Bernardo Cortez, Florian Peter, Thomas Lausenhammer, Paulo Oliveira

Abstract:

Designing missiles’ autopilot controllers have been a complex task, given the extensive flight envelope and the nonlinear flight dynamics. A solution that can excel both in nominal performance and in robustness to uncertainties is still to be found. While Control Theory often debouches into parameters’ scheduling procedures, Reinforcement Learning has presented interesting results in ever more complex tasks, going from videogames to robotic tasks with continuous action domains. However, it still lacks clearer insights on how to find adequate reward functions and exploration strategies. To the best of our knowledge, this work is a pioneer in proposing Reinforcement Learning as a framework for flight control. In fact, it aims at training a model-free agent that can control the longitudinal non-linear flight dynamics of a missile, achieving the target performance and robustness to uncertainties. To that end, under TRPO’s methodology, the collected experience is augmented according to HER, stored in a replay buffer and sampled according to its significance. Not only does this work enhance the concept of prioritized experience replay into BPER, but it also reformulates HER, activating them both only when the training progress converges to suboptimal policies, in what is proposed as the SER methodology. The results show that it is possible both to achieve the target performance and to improve the agent’s robustness to uncertainties (with low damage on nominal performance) by further training it in non-nominal environments, therefore validating the proposed approach and encouraging future research in this field.

Keywords: Reinforcement Learning, flight control, HER, missile autopilot, TRPO

Procedia PDF Downloads 258

Authors: Negar Sartipzadeh

Abstract:

The historic buildings are generally the ones which have been built by materials like brick, mud, stone, and wood. Some phenomena such as severe earthquakes can be tremendously detrimental to the structures, imposing serious effects and losses on such structures. Hence, it matters a lot to ascertain safety and reliability of the structures under such circumstances. It has been asserted that the major reason for the collapse of Unreinforced Masonry (URM) in various earthquakes is the incapability of resisting the forces and vice versa because such URMs are meant for the gravity load and they fail to withstand the shear forces inside the plate and the bending forces outside the plate. For this reason, restrengthening such structures is a key factor in lowering the seismic loss in developing countries. Seismic reinforcement of the historic buildings with regard to their cultural value on one hand, and exhaustion and damage of many of the structural elements on the other hand, have brought in restricting factors which necessitate the seismic reinforcement methods meant for such buildings to be maximally safe, non-destructive, effective, and non-obvious. Henceforth, it is pinpointed that making use of diverse technologies such as active controlling, Energy dampers, and seismic separators besides the current popular methods would be justifiable for such buildings, notwithstanding their high imposed costs.

Keywords: masonry buildings, seismic reinforcement, Unreinforced Masonry (URM), earthquake

Procedia PDF Downloads 274

Authors: Jagdish Prasad Sahoo

Abstract:

The increase in active earth pressure during the event of an earthquake results sliding, overturning and tilting of earth retaining structures. In order to improve upon the stability of structures, the soil mass is often reinforced with various types of reinforcements such as metal strips, geotextiles, and geogrids etc. The stresses generated in the soil mass are transferred to the reinforcements through the interface friction between the earth and the reinforcement, which in turn reduces the lateral earth pressure on the retaining walls. Hence, the evaluation of earth pressure in the presence of seismic forces with an inclusion of reinforcements is important for the design retaining walls in the seismically active zones. In the present analysis, the effect of reinforcing horizontal layers of reinforcements in the form of sheets (Geotextiles and Geogrids) in sand used as backfill, on reducing the active earth pressure due to earthquake body forces has been studied. For carrying out the analysis, pseudo-static approach has been adopted by employing upper bound theorem of limit analysis in combination with finite elements and linear optimization. The computations have been performed with and out reinforcements for different internal friction angle of sand varying from 30 ° to 45 °. The effectiveness of the reinforcement in reducing the active earth pressure on the retaining walls is examined in terms of active earth pressure coefficient for presenting the solutions in a non-dimensional form. The active earth pressure coefficient is expressed as functions of internal friction angle of sand, interface friction angle between sand and reinforcement, soil-wall interface roughness conditions, and coefficient of horizontal seismic acceleration. It has been found that (i) there always exists a certain optimum depth of the reinforcement layers corresponding to which the value of active earth pressure coefficient becomes always the minimum, and (ii) the active earth pressure coefficient decreases significantly with an increase in length of reinforcements only up to a certain length beyond which a further increase in length hardly causes any reduction in the values active earth pressure. The optimum depth of the reinforcement layers and the required length of reinforcements corresponding to the optimum depth of reinforcements have been established. The numerical results developed in this analysis are expected to be useful for purpose of design of retaining walls.

Keywords: active, finite elements, limit analysis, presudo-static, reinforcement

Procedia PDF Downloads 357

Authors: Albert Bou, Sebastian Dittert, Gianni de Fabritiis

Abstract:

Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries advocate for highly modular agent composability, which facilitates experimentation and development. To solve challenging environments within reasonable time frames, scaling RL to large sampling and computing resources has proved a successful strategy. However, this capability has been so far difficult to combine with modularity. In this work, we explore design choices to allow agent composability both at a local and distributed level of execution. We propose a versatile approach that allows the definition of RL agents at different scales through independent, reusable components. We demonstrate experimentally that our design choices allow us to reproduce classical benchmarks, explore multiple distributed architectures, and solve novel and complex environments while giving full control to the user in the agent definition and training scheme definition. We believe this work can provide useful insights to the next generation of RL libraries.

Keywords: deep reinforcement learning, Python, PyTorch, distributed training, modularity, library

Procedia PDF Downloads 78

Authors: Dhval Chauhan, Mahesh Chudasama

Abstract:

This study has been undertaken to give a review of Polyethylene Terephthalate Glycol (PETG) material used in Fused Deposition Modelling (FDM). This paper offers a review of the existing literature on polyethylene terephthalate glycol (PETG) material, the objective of the paper is to providing guidance on different process parameters that can be used to improve the strength of the part by performing various testing like tensile, compressive, flexural, etc. This work is target to find new paths that can be used for further development of the use of fiber reinforcement in PETG material.

Keywords: PETG, FDM, tensile strength, flexural strength, fiber reinforcement

Procedia PDF Downloads 187

Authors: Sirapop Nuannimnoi, Hojjat Baghban, Ching-Yao Huang

Abstract:

Over the past decade, with the fast development of blockchain technology since the birth of Bitcoin, there has been a massive increase in the usage of Cryptocurrencies. Cryptocurrencies are not seen as an investment opportunity due to the market’s erratic behavior and high price volatility. With the recent success of deep reinforcement learning (DRL), portfolio management can be modeled and automated. In this paper, we propose a novel DRL-based multi-agent system to automatically make proper trading decisions on multiple cryptocurrencies and gain profits in the highly volatile cryptocurrency market. We also extend this multi-agent system with horizontal federated transfer learning for better adapting to the inclusion of new cryptocurrencies in our portfolio; therefore, we can, through the concept of diversification, maximize our profits and minimize the trading risks. Experimental results through multiple simulation scenarios reveal that this proposed algorithmic trading system can offer three promising key advantages over other systems, including maximized profits, minimized risks, and adaptability.

Keywords: cryptocurrency portfolio management, algorithmic trading, federated learning, multi-agent reinforcement learning

Procedia PDF Downloads 112

Authors: Akshay Paranjape, Nils Plettenberg, Robert Schmitt

Abstract:

Producing faulty products can be costly for manufacturing companies and wastes resources. To reduce scrap rates in manufacturing, process parameters can be optimized using machine learning. Thus far, research mainly focused on optimizing specific processes using traditional algorithms. To develop a framework that enables real-time optimization based on a predictive model for an arbitrary production process, this study explores the application of reinforcement learning (RL) in this field. Based on a thorough review of literature about RL and process parameter optimization, a model based on maximum a posteriori policy optimization that can handle both numerical and categorical parameters is proposed. A case study compares the model to state–of–the–art traditional algorithms and shows that RL can find optima of similar quality while requiring significantly less time. These results are confirmed in a large-scale validation study on data sets from both production and other fields. Finally, multiple ways to improve the model are discussed.

Keywords: reinforcement learning, production process optimization, evolutionary algorithms, policy optimization, actor critic approach

Procedia PDF Downloads 90

Authors: C. P. Providakis, G. M. Angeli, M. J. Favvata, N. A. Papadopoulos, C. E. Chalioris, C. G. Karayannis

Abstract:

An effort for the detection of damages in the reinforcement bars of reinforced concrete members using PZTs is presented. The damage can be the result of excessive elongation of the steel bar due to steel yielding or due to local steel corrosion. In both cases the damage is simulated by considering reduced diameter of the rebar along the damaged part of its length. An integration approach based on both electromechanical admittance methodology and guided wave propagation technique is used to evaluate the artificial damage on the examined longitudinal steel bar. Two actuator PZTs and a sensor PZT are considered to be bonded on the examined steel bar. The admittance of the Sensor PZT is calculated using COMSOL 3.4a. Fast Furrier Transformation for a better evaluation of the results is employed. An effort for the quantification of the damage detection using the root mean square deviation (RMSD) between the healthy condition and damage state of the sensor PZT is attempted. The numerical value of the RSMD yields a level for the difference between the healthy and the damaged admittance computation indicating this way the presence of damage in the structure. Experimental measurements are also presented.

Keywords: concrete reinforcement, damage detection, electromechanical admittance, experimental measurements, finite element method, guided waves, PZT

Procedia PDF Downloads 247

Authors: C. P. Providakis, G. M. Angeli, M. J. Favvata, N. A. Papadopoulos, C. E. Chalioris, C. G. Karayannis

Abstract:

An effort for the detection of damages in the reinforcement bars of reinforced concrete members using PZTs is presented. The damage can be the result of excessive elongation of the steel bar due to steel yielding or due to local steel corrosion. In both cases the damage is simulated by considering reduced diameter of the rebar along the damaged part of its length. An integration approach based on both electro-mechanical admittance methodology and guided wave propagation technique is used to evaluate the artificial damage on the examined longitudinal steel bar. Two actuator PZTs and a sensor PZT are considered to be bonded on the examined steel bar. The admittance of the Sensor PZT is calculated using COMSOL 3.4a. Fast Furrier Transformation for a better evaluation of the results is employed. An effort for the quantification of the damage detection using the root mean square deviation (RMSD) between the healthy condition and damage state of the sensor PZT is attempted. The numerical value of the RSMD yields a level for the difference between the healthy and the damaged admittance computation indicating this way the presence of damage in the structure. Experimental measurements are also presented.

Keywords: concrete reinforcement, damage detection, electromechanical admittance, experimental measurements, finite element method, guided waves, PZT

Procedia PDF Downloads 285

Authors: Brwa Abdulrahman Abubaker

Abstract:

Recently, there has been a lot of interest in the difficult task of applying reinforcement learning to autonomous mobile robots. Conventional reinforcement learning (TRL) techniques have many drawbacks, such as lengthy computation times, intricate control frameworks, a great deal of trial and error searching, and sluggish convergence. In this paper, a modified Spiking Neural Network (SNN) is used to offer a distinct method for autonomous mobile robot learning and control in unexpected surroundings. As a learning algorithm, the suggested model combines dopamine modulation with spike-timing-dependent plasticity (STDP). In order to create more computationally efficient, biologically inspired control systems that are adaptable to changing settings, this work uses the effective and physiologically credible Izhikevich neuron model. This study is primarily focused on creating an algorithm for target tracking in the presence of obstacles. Results show that the SNN trained with three obstacles yielded an impressive 96% success rate for our proposal, with collisions happening in about 4% of the 214 simulated seconds.

Keywords: spiking neural network, spike-timing-dependent plasticity, dopamine modulation, reinforcement learning

Procedia PDF Downloads 4

Authors: Zaidour Mohamed, Ghalem Ali Jr., Achit Henni Mohamed

Abstract:

This project is destined to study pole junctions of reinforced concrete beams subjected to seismic loads. A literature review was made to clarify the work done by researchers in the last three decades and especially the results of the last two years that were studied for the determination of the method of calculating the transverse reinforcement in the different nodes of a structure. For implementation efforts in the columns and beams of a building R + 4 in zone 3 were calculated using the finite element method through software. These results are the basis of our work which led to the calculation of the transverse reinforcement of the nodes of the structure in question.

Keywords: beam–column joints, cyclic loading, shearing force, damaged joint

Procedia PDF Downloads 539

Authors: Romisaa Ali

Abstract:

This paper presents a comparison between twin-delayed Deep Deterministic Policy Gradient (TD3) and Soft Actor-Critic (SAC) reinforcement learning algorithms in the context of training robust navigation policies for Jackal robots. By leveraging an open-source framework and custom motion control environments, the study evaluates the performance, robustness, and transferability of the trained policies across a range of scenarios. The primary focus of the experiments is to assess the training process, the adaptability of the algorithms, and the robot’s ability to navigate in previously unseen environments. Moreover, the paper examines the influence of varying environmental complexities on the learning process and the generalization capabilities of the resulting policies. The results of this study aim to inform and guide the development of more efficient and practical reinforcement learning-based navigation policies for Jackal robots in real-world scenarios.

Keywords: Jackal robot environments, reinforcement learning, TD3, SAC, robust navigation, transferability, custom environment

Procedia PDF Downloads 93

Authors: S. Bahadır Yüksel, Alptuğ Ünal

Abstract:

The composite shear walls (CSW) with steel encased profiles can be used as lateral-load resisting systems for buildings that require considerable large lateral-load capacity. The aim of this work is to propose the experimental work conducted on CSW having L section folded plate (L shape steel made-up sections) as longitudinal reinforcement in boundary regions. The study in this paper present the experimental test conducted on CSW having L section folded plate as longitudinal reinforcement in boundary regions. The tested 1/3 geometric scaled CSW has aspect ratio of 3.2. L-shape structural steel materials with 2L-19x57x7mm dimensions were placed in shear wall boundary zones. The seismic behavior of CSW test specimen was investigated by evaluating and interpreting the hysteresis curves, envelope curves, rigidity and consumed energy graphs of this tested element. In addition to this, the experimental results, deformation and cracking patterns were evaluated, interpreted and suggestions of the design recommendations were proposed.

Keywords: shear wall, composite shear wall, boundary reinforcement, earthquake resistant structural design, L section

Procedia PDF Downloads 323