Traditional Reinforcement Research Articles

An investigation on the bond behavior of basalt fiber reinforced polymer (BFRP) rebars embedded in conventional concrete

This research investigates the bond behavior of basalt fiber-reinforced polymer (BFRP) bars in conventional concrete, focusing on its relation to mild steel bar bond behavior and the magnitude of variation. Using BFRP as a replacement for traditional mild steel reinforcement has gained attention due to its inherent corrosion resistance and high tensile strength properties. In environments where steel corrosion poses a significant threat to structural integrity, BFRP offers a promising alternative for improving the long-term durability and longevity of reinforced concrete members and structures. The study aims to evaluate the bond strength between BFRP rebars embedded in conventional concrete through experimental testing and analysis. Various factors affecting bond performance, including surface preparation, embedment length, and concrete mix design, are considered. The findings of this research contribute to a better understanding of the feasibility and effectiveness of utilizing BFRP reinforcement in concrete structures, particularly in mitigating the challenges associated with steel corrosion. Ultimately, the results aim to inform engineering practices and promote the adoption of sustainable and corrosion-resistant materials for infrastructure development, thereby addressing a critical need in the field. The results are also compared to the current ACI 440 bond equation and database of other BFRP data collected by the authors.

A method for solving reconfiguration blueprints based on multi-agent reinforcement learning

Integrated modular avionics systems primarily achieve system fault tolerance by reconfiguring the system configuration blueprints. In the design of manual reconfiguration, the quality of reconfiguration blueprints is influenced by various unstable factors, leading to a certain degree of uncertainty. The effectiveness of reconfiguration blueprints depends on various factors, including load balancing, the impact of reconfiguration, and the time required for the process. Solving high-quality reconfiguration configuration blueprints can be regarded as a type of multi-objective optimization problem. Traditional algorithms have limitations in solving multi-objective optimization problems. Multi-Agent Reinforcement Learning (MARL) is an important branch in the field of machine learning. It enables the accomplishment of more complex tasks in dynamic real-world scenarios through interaction and decision-making. Combining Multi-Agent Reinforcement Learning algorithms with reconfiguration techniques and utilizing MARL methods to generate blueprints can optimize the quality of blueprints in multiple ways. In this paper, an Improved Value-Decomposition Networks (VDN) based on the average sequential cumulative reward is proposed. By refining the characteristics of the integrated modular avionics system, mathematical models are developed for both the system and the reconfiguration blueprint. The Improved VDN algorithm demonstrates superior convergence characteristics and optimization effects compared with traditional reinforcement learning algorithms such as Q-learning, Deep Q-learning Network (DQN), and VDN. This superiority has been confirmed through experiments involving single and continuous faults.

Critical Evaluation of Vertical Stud Integration for Enhancing Blast Resistance in Slabs: A Comparative Analysis with Traditional Reinforcement Methods

Critical Evaluation of Vertical Stud Integration for Enhancing Blast Resistance in Slabs: A Comparative Analysis with Traditional Reinforcement Methods

Influence of PLA impregnation on the performances of vegetable fibers for lime-based composites

In recent years, the application of inorganic lime-based Textile Reinforced Mortar (TRM) for repairing existing masonry structures has gained a relevant interest due to the strong compatibility between masonry elements and the strengthening composite. In addition, several research groups worldwide have recently focused on the possible use of natural fibers for replacing the traditional reinforcement (e.g., steel, fiberglass, basalt, PBO, aramid, carbon, etc.) generally employed for TRM composites. As a matter of fact, the natural fabrics (easily available and biodegradable) present comparable resistance to conventional fabrics, good compatibility with the lime-based mortars and elastic modules compatible with masonry elements. On the other hand, it has been also demonstrated that one of the most relevant aspects on their possible application is related their long-term and durability performances which can be mitigated with coating and impregnation treatments. In this context, the present paper presents the preliminary result of an experimental research aimed at investigating the influence of a biodegradable coating system (PLA - polylactic acid) applied to different types of natural fibers (made of flax and jute) on the resulting performances either from the physical and mechanical standpoint. The results demonstrate a significant improvement of the observed performance of natural fibers that can be more properly employed for the production of natural TRM composites.

Safe Transfer-Reinforcement-Learning-Based Optimal Control of Nonlinear Systems.

Traditional reinforcement learning (RL) methods for optimal control of nonlinear processes often face challenges, such as high computational demands, long training times, and difficulties in ensuring the safety of closed-loop systems during training. To address these issues, this work proposes a safe transfer RL (TRL) framework. The TRL algorithm leverages knowledge from pretrained source tasks to accelerate learning in a new, related target task, significantly reducing both learning time and computational resources required for optimizing control policies. To ensure safety during knowledge transfer and training, data collection and optimization of the control policy are performed within a control invariant set (CIS) throughout the learning process. Furthermore, we theoretically analyze the errors between the approximate and optimal control policies by accounting for the differences between source and target tasks. Finally, the proposed TRL method is applied to the case studies of chemical processes to demonstrate its effectiveness in solving the optimal control problem with improved computational efficiency and guaranteed safety.

Static load test of unreinforced Franchi (B-4350) soil reinforcement pile

Micro-pile drilling technology is often used today for the reconstruction and repair of buildings whose foundations are heavily loaded. Once installed, the piles take up part of this load. They can also be used to improve the load-bearing capacity of building foundations before the upper floors are built on top of them or before additional underground floors are constructed. Construction of buildings and structures in areas with complex soils is a special case. Buildings constructed in such conditions as a result of underground mining operations, soil movement into the excavated space and formation of a displacement trough on the ground surface are subjected to uneven settlement and horizontal deformations during operation. This paper presents the results of field tests of unreinforced Franki micro-pile (B-4350) unreinforced pile for soil reinforcement. Based on the obtained data, it can be concluded that the use of micro-piles to reinforce the foundations of reconstructed buildings provides a reduction in construction costs, labor costs and construction time, and as a consequence demonstrates their undeniable effectiveness. Application of micro-piles at reinforcement of strip foundations, in comparison with the traditional reinforcement design gives reduction of the estimated cost of construction (by 8 %), mainly due to reduction of the cost of operation of machines (by 46 %) and reduction of wages (by 24 %), though with some increase in the cost of materials (by 28 %), which somewhat levels out the general tendencies of cost reduction.

Evaluation of flexural failure for concrete beams partially reinforced by geogrid sheets

ABSTRACT The behavior of reinforced concrete beams with biaxial and uniaxial geogrids as a partial reinforcement with traditional steel bars under flexural loads has been experimentally studied. The effect of geogrid layers with traditional steel reinforcement in concrete beam specimens in compression and tension zones has also been investigated. Geogrid is one of the geosynthetic materials that exhibits both tensile and flexural behavior similar to traditional steel. To examine the effect of geogrids on traditional steel as a composite reinforcement system, strain gauges were fixed to the concrete beams and bottom reinforcement (steel bars). The studied parameters in this investigation are the number of geogrid layers, types of geogrids, and their position in concrete beams. First cracking load, failure load, initial and post-cracking, deflection, and ductility of beam specimen were investigated. The experimental results indicated that using geogrid sheet layers as partial reinforcement greatly contributed to resisting flexural stresses of concrete beams. An increase in the ductility and the capacity load of the concrete beam specimen was also observed. Based on this experimental investigation, the geogrids can be applied as additional or alternative reinforcement with/without traditional steel bars in concrete beams.

Object Detection for Reinforcement Learning Agents

In traditional reinforcement learning applications with images as input, the observation for the agent to learn from, is an image. In these models, a Convolutional Neural Network (CNN) is typically used to extract the features before for the learning process, in order to maximize the cumulative reward. In this paper, a different approach for pre-processing the input for reinforcement learning agents is considered. The proposed approach uses object detectors instead instead of CNNs, and converts each input image into bounding boxes and object locations for the agent to learn from.

Study on the Methods of Strengthening Reinforced Concrete Beams with CFRP

After the long-term use of reinforced concrete structures, there may be structural aging and structural damage, these common engineering problems. As a result, the performance is reduced, so it is necessary to strengthen to meet the corresponding safety requirements. Carbon Fiber Reinforced Polymer (CFRP) has the advantages of lightweight, strong, high tensile strength and tensile degree. Therefore, CFRP is widely used in reinforcement. Based on CFRP reinforcement of reinforced concrete beams, this paper analyzes its reinforcement methods. The paper mainly analyzes the influence of different pasting methods of CFRP on the performance of beams and the influence of material pasting thickness on beams. Through the analysis and research, it can be concluded that CFRP has certain advantages compared with traditional reinforcement materials. Therefore, it can be used to reinforce reinforced concrete beams. This study can provide some reference value for some related projects of reinforced concrete beams reinforced by CFRP.

Enhancing urban metro system resilience under disruptive events through multi-agent reinforcement learning

With urban rail transit (URT) systems playing an increasingly crucial role in megacity mobility, the rising frequency of service disruptions may pose substantial passenger delays and safety concerns. This emphasizes the need to prioritize resilience enhancements for the URT system. Bus bridging, an effective resilience-enhancing measure, faces challenges that effectively capture the unique features of bridging buses and stranded passengers, and rely on predetermined routes and fixed frequencies, diminishing service flexibility and efficiency in dynamic bridging environments. To overcome these challenges, we propose a novel approach using a multi-agent reinforcement learning model. This model treats bus bridging as a collaborative multi-agent task with the competition. Specifically, it enables bridging buses to adaptively select the next visiting station based on environmental characteristics. Furthermore, a competitive reward function is introduced to facilitate effective collaboration among all agents while preventing malicious competition. The case study results demonstrate that the proposed enhancing resilience method outperforms traditional reinforcement learning method and classic bus bridging strategy and can reduce the average waiting time and average travel time, especially in resource-limited and complex scenarios.

A NEW APPROACH TO TENSILE TESTING OF GFRP BARS

Tensile testing is a critical procedure for evaluating the mechanical properties of Glass Fiber Reinforced Polymer (GFRP) bars, which emerged as an alternative to traditional steel reinforcement in reinforced concrete structures. While significant research has led to the development of testing standards for GFRP bars, their implementation often necessitates additional specimens and specialized equipment compared to their steel counterparts. This study proposes a new method for conducting GFRP tensile tests using standard equipment designed for conventional structural steel rebar testing. By employing existing devices, our approach offers a practical and cost-effective solution for assessing the tensile properties of GFRP reinforcement. This simplified testing method aims to enhance efficiency, facilitate wider adoption of GFRP bars in reinforced concrete structures, and contribute to the advancement of sustainable construction practices.

Active Predictive Coding: A Unifying Neural Model for Active Perception, Compositional Learning, and Hierarchical Planning.

There is growing interest in predictive coding as a model of how the brain learns through predictions and prediction errors. Predictive coding models have traditionally focused on sensory coding and perception. Here we introduce active predictive coding (APC) as a unifying model for perception, action, and cognition. The APC model addresses important open problems in cognitive science and AI, including (1) how we learn compositional representations (e.g., part-whole hierarchies for equivariant vision) and (2) how we solve large-scale planning problems, which are hard for traditional reinforcement learning, by composing complex state dynamics and abstract actions from simpler dynamics and primitive actions. By using hypernetworks, self-supervised learning, and reinforcement learning, APC learns hierarchical world models by combining task-invariant state transition networks and task-dependent policy networks at multiple abstraction levels. We illustrate the applicability of the APC model to active visual perception and hierarchical planning. Our results represent, to our knowledge, the first proof-of-concept demonstration of a unified approach to addressing the part-whole learning problem in vision, the nested reference frames learning problem in cognition, and the integrated state-action hierarchy learning problem in reinforcement learning.

Ketamine produces no detectable long-term positive or negative effects on cognitive flexibility or reinforcement learning of male rats.

Patients with major depressive disorder (MDD) often experience abnormalities in behavioral adaptation following environmental changes (i.e., cognitive flexibility) and tend to undervalue positive outcomes but overvalue negative outcomes. The probabilistic reversal learning task (PRL) is used to study these deficits across species and to explore drugs that may have therapeutic value. Selective serotonin-reuptake inhibitors (SSRIs) have limited effectiveness in treating MDD and produce inconsistent effects in non-human versions of the PRL. As such, ketamine, a novel and potentially rapid-acting therapeutic, has begun to be examined using the PRL. Two previous studies examining the effects of ketamine in the PRL have shown conflicting results and only examined short-term effects of ketamine. This experiment examined PRL performance across a 2-week period following a single exposure to a ketamine dose that varied across groups. After five sessions of PRL training, groups of rats received an injection of either 0, 10, 20 or 30 mg/kg ketamine. One-hour post-injection, rats engaged in the PRL, and subsequently sessions continued daily for 2 weeks. Traditional behavioral and computational reinforcement learning-derived measures were examined. Results showed that ketamine had acute effects 1-h post-injection, including a significant decrease in the value of the punishment learning rate. Beyond 1 h, ketamine produced no detectable improvements nor decrements in performance across 2 weeks. Overall, the present results suggest that the range of ketamine doses examined do not have long-term positive or negative effects on cognitive flexibility or reward processing in healthy rats as measured by the PRL.

Numerical analysis of GFRP rebar embedded concrete beam

The use of glass fiber-reinforced polymer (GFRP) in construction has several sustainability benefits that make it an attractive alternative to traditional reinforcement materials. One of the main sustainability problems faced by steel is its carbon footprint, 1.89 tonnes of CO2 is being released into the atmosphere for every tonne of steel produced. Another wellknown problem faced by steel in construction is corrosion which is the leading cause of failure of a building. the use of GFRP in construction offers several sustainability benefits that make it an attractive alternative for use in a variety of applications. The combination of improved performance, reduced waste, and lower carbon footprint make GFRP a sustainable choice for the construction industry. This paper presents a numerical analysis of a concrete beam reinforced with glass fiber-reinforced polymer (GFRP) rebar. The study aims to investigate the mechanical behaviours and performance of concrete beams embedded with GFRP rebar under 2-point loading conditions. Ansys 2023 software was utilised for the modelling and analysis of the developed model. Two models were created in the Ansys workbench, one with GFRP rebar as reinforcement and other with steel rebar reinforcement. The numerical results were then analysed to determine the load-carrying capacity and deformation behaviours of the GFRP-reinforced concrete beams compared to that of regular steel reinforced beam.

3D printed concrete beams as optimised load carrying structural elements – The Minimass beam

3D printed concrete structures have not been widely developed outside the realms of compression-only cases such as walls and columns. The Minimass beam is proposed as an approach to design and manufacture beams, which resist bending primarily through axial compression and tension. This is achieved using 3D printing of concrete for compression elements and external steel cable reinforcing for tension elements but without traditional reinforcement in the concrete itself. This paper presents the justification and benefits of such an approach. It also presents a series of load tests on physical prototypes, describing the performance and results. The different failure modes are discussed, with suggestions for improvements and a focus on the outlook for the future.

Sliding principal component and dynamic reward reinforcement learning based IIoT attack detection

The Internet of Things (IoT) involves the gathering of all those devices that connect to the Internet with the purpose of collecting and sharing data. The application of IoT in the different sectors, including health, industry has also picked up the threads to augment over the past few years. The IoT and, by integrity, the IIoT, are found to be highly susceptible to different types of threats and attacks owing to the networks nature that in turn leads to even poor outcomes (i.e., increasing error rate). Hence, it is critical to design attack detection systems that can provide the security of IIoT networks. To overcome this research work of IIoT attack detection in large amount of evolutions is failed to determine the certain attacks resulting in a minimum detection performance, reinforcement learning-based attack detection method called sliding principal component and dynamic reward reinforcement learning (SPC–DRRL) for detecting various IIoT network attacks is introduced. In the first stage of this research methodology, preprocessing of raw TON_IoT dataset is performed by employing min–max normalization scaling function to obtain normalized values with same scale. Next, with the processed sample data as output, to extract data from multi-sources (i.e., different service profiles from the dataset), a robust log likelihood sliding principal component-based feature extraction algorithm is applied with an arbitrary size sliding window to extract computationally-efficient features. Finally, dynamic reward reinforcement learning-based IIoT attack detection model is presented to control the error rate involved in the design. Here, with the design of dynamic reward function and introducing incident repository that not only generates the reward function in an arbitrary fashion but also stores the action results in the incident repository for the next training, therefore reducing the attack detection error rate. Moreover, an IIoT attack detection system based on SPC–DRRL is constructed. Finally, we verify the algorithm on the ToN_IoT dataset of University of New South Wales Australia. The experimental results show that the IIoT attack detection time and overhead along with the error rate are reduced considerably with higher accuracy than that of traditional reinforcement learning methods.

Analysis of the Effect of Ultra-Fine Cement on the Microscopic Pore Structure of Cement Soil in a Peat Soil Environment

Treating peat soil foundations around Dianchi Lake and Erhai Lake in Yunnan is a complex problem in practical engineering projects. Peat soil solely reinforced with ordinary cement (OPC) does not satisfy demand. This study aims to solidify soil to achieve better mechanical properties. The preparation of peat soil incorporates a humic acid (HA) reagent into cohesive soil, and cement and ultra-fine cement (UFC) are mixed by stirring to prepare cement soil samples. They are then immersed in fulvic acid (FA) solution to simulate cement soil in the actual environment. X-ray diffraction (XRD), mercury intrusion porosimetry (MIP), scanning electron microscopy (SEM), and pores and cracks analysis system (PCAS) tests are used to study the impact of the UFC on the microscopic pore structure of cement soil in a peat soil environment. The unconfined compressive strength (UCS) test is used for verification. The microscopic test results indicate that incorporating UFC enhances the specimen’s micropore structure. The XRD test results show the presence of C–S–H, C–A–S–H, and C–A–H. SEM and PCAS tests show that the UFC proportion increases by between 0% and 10%, and the percentage reduction in the macropore volume is the largest, at 38.84%. When the UFC admixture is 30%, the cumulative reduction in the percentage of macropore volume reaches 71.55%. The MIP test results show that the cumulative volume greater than 10 µm in pore size decreases from 7.68% to 0.17% with an increase in the UFC proportion. The UCS test results show that the maximum strength growth of cement soil is 12.99% when the UFC admixture is 0–10%. Incorporating UFC to form a compound curing agent solves the problem of the traditional reinforcement treatment of peat soil foundation being undesirable and decreases the amount of cement. This study provides practical guidance for reducing carbon emissions in actual projects.

Mean Field Multi-Agent Reinforcement Learning Method for Area Traffic Signal Control

Reinforcement learning is an effective method for adaptive traffic signal control in urban transportation networks. As the number of training rounds increases, the optimal control strategy is learned, and the learning capabilities of deep neural networks are further enhanced, thereby avoiding the limitations of traditional signal control methods. However, when faced with the sequential decision tasks of regional signal control, it encounters issues such as the curse of dimensionality and environmental non-stationarity. To address the limitations of traditional reinforcement learning algorithms applied to multiple intersections, the mean field theory is applied. This models the traffic signal control problem at multiple intersections within a region as interactions between individual intersections and the average effects of neighboring intersections. By decomposing the Q-function through bilateral estimation between the agent and its neighbors, this method reduces the complexity of interactions between agents while preserving global interactions between the agents. A traffic signal control model based on Mean Field Multi-Agent Reinforcement Learning (MFMARL) was constructed, containing two algorithms: Mean Field Q-Network Area Traffic Signal Control (MFQ-ATSC) and Mean Field Actor-Critic Network Area Traffic Signal Control (MFAC-ATSC). The model was validated using the SUMO simulation platform. The experimental results indicate that across different metrics, such as average speed, the mean field reinforcement learning method outperforms classical signal control methods and several existing approaches.

In-Situ Test and Numerical Simulation of Anchoring Performance of Embedded Rock GFRP Anchor

Compared to traditional steel reinforcement, GFRP anchors demonstrate outstanding mechanical performance and corrosion resistance, and so they are an ideal substitute for steel reinforcement in anti-floating projects. Based on finite element software, a 3D axisymmetric calculation model of GFRP anti-floating anchors in medium-weathered granite was established in this paper. Combined with the in-situ ultimate pull-out tests, the bonding anchoring performance and bearing characteristics between the anchor body, anchoring mortar, and rock–soil mass were analyzed. The research findings indicated that the cohesive bonding elements exhibited a high degree of conformity in defining the interface contact relationship of the GFRP anti-floating anchor anchoring system. The axial force of the GFRP anti-floating anchor body is “attenuated” along the depth direction, and there was a critical value of anchoring length; under the same conditions, the reasonable anchoring length should be 3.5~5.0 m. All the anchors in the in-situ tests exhibited interfacial shear slip failure between the anchor body and the anchor mortar, with an average maximum load of 450 kN, which is consistent with the maximum failure load of the simulated anchors. Compared to a load of 50 kN, the maximum stress of the anchor mortar increased by 50% under a load of 450 kN. The displacement variation of the surrounding rock–soil mass showed a decreasing trend from the inside to the outside and from the top to the bottom. The research results provided valuable references for the optimization design of GFRP anti-floating anchors.

Structural detection and reinforcement methods for existing buildings

With the popularity of building construction worldwide, building design, construction technology and quality are faced with inherent deficiencies and may be hit by disasters. Therefore, the diagnosis and reinforcement of building structure has become a major problem to be solved urgently in the current building construction. This paper introduces simple detection methods of different building structures and reinforcement techniques under different conditions. In the part of detection methods, various basic detection methods of normal building structure are studied. Then, a special damage appearance is discussed. Besides the traditional electronic imaging method to detect cracks, a special method is proposed to solve the crack problem, namely Min-Max Gray Level Discrimination (M2GLD). This method can improve the detection accuracy and reduce the influence of human factors. At the same time, several different reinforcement techniques are proposed, including traditional reinforcement techniques and advanced reinforcement techniques. This paper introduces the traditional technology of ancient timber structures and the technology of spraying and external bonding FRP to enhance flexural, shear and compressive strength. This paper can be used as reference for structural inspection and reinforcement of existing buildings.