Dimensionality reduction and prediction of soil consolidation coefficient using random forest coupling with Relief algorithm

The consolidation coefficient of soil (C_v) is a crucial parameter used for the design of structures leaned on soft soi. In general, the C_v is determined experimentally in the laboratory. However, the experimental tests are time-consuming as well as expensive. Therefore, researchers tried several ways to determine C_v via other simple soil parameters. In this study, we developed a hybrid model of Random Forest coupling with a Relief algorithm (RF-RL) to predict the C_v of soil. To conduct this study, a database of soil parameters collected from a case study region in Vietnam was used for modeling. The performance of the proposed models was assessed via statistical indicators, namely Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The proposal models were constructed with four sets of soil variables, including 6, 7, 8, and 13 inputs. The results revealed that all models performed well with a high performance (R² > 0.980). Although the RF-RL model with 13 variables has the highest prediction accuracy ( R² = 0.9869), the difference compared with other models was negligible (i.e., R² = 0.9824, 0.9850, 0.9825 for the cases with 6, 7, 8 inputs, respectively). Thus, it can be concluded that the hybrid model of RF-RL can be employed to predict C_v based on the basic soil parameters.     

Assessment of different machine learning techniques in predicting the compressive strength of self-compacting concrete

The compressive strength of self-compacting concrete (SCC) needs to be determined during the construction design process. This paper shows that the compressive strength of SCC (CS of SCC) can be successfully predicted from mix design and curing age by a machine learning (ML) technique named the Extreme Gradient Boosting (XGB) algorithm, including non-hybrid and hybrid models. Nine ML techniques, such as Linear regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees (DTR), Random Forest (RF), Gradient Boosting (GB), and Artificial Neural Network using two training algorithms LBFGS and SGD (denoted as ANN_LBFGS and ANN_SGD), are also compared with the XGB model. Moreover, the hybrid models of eight ML techniques and Particle Swarm Optimization (PSO) are constructed to highlight the reliability and accuracy of SCC compressive strength prediction by the XGB_PSO hybrid model. The highest number of SCC samples available in the literature is collected for building the ML techniques. Compared with previously published works’ performance, the proposed XGB method, both hybrid and non-hybrid models, is the most reliable and robust of the examined techniques, and is more accurate than existing ML methods (R² = 0.9644, RMSE = 4.7801, and MAE = 3.4832). Therefore, the XGB model can be used as a practical tool for engineers in predicting the CS of SCC.     

Effect of W/C ratio on covering depth of fly ash concrete in marine environment

This investigation studied the effect of W/C ratio on covering depth required against the corrosion of embedded steel of fly ash concrete in marine environment up to 4-year exposure. Fly ash was used to partially replace Portland cement type I at 0%, 15%, 25%, 35%, and 50% by weight of cementitious material. Water to cementitious material ratios (W/C) of fly ash concretes were varied at 0.45, 0.55, and 0.65. The 200-mm concrete cube specimens were cast and steel bars with 12-mm diameter and 50 mm in length were inserted in the concrete with the covering depth of 10, 20, 50, and 75 mm. The specimens were cured in water for 28 days, and then placed to the tidal zone of marine environment in the Gulf of Thailand. Subsequently, the concrete specimens were tested for the compressive strength, chloride penetration profile and corrosion of embedded steel bar after being exposed to tidal zone for 2, 3, and 4 years. The results showed that the concrete mixed with Portland cement type I exhibited higher rate of the chloride penetration than the fly ash concrete. The chloride penetration of fly ash concrete was comparatively low and decreased with the increasing of fly ash content. The increase of fly ash replacement and the decrease of W/C ratio could reduce the covering depth required for the initial corrosion of the steel bar. Interestingly, fly ash concretes with 35% and 50% cement replacement and having W/C ratio of 0.65 provided better corrosion resistance at 4-year exposure than the control concrete with W/C ratio of 0.45. In addition, the covering depth of concrete with compressive strength of 30 MPa (W/C ratio of 0.65) could be reduced from 50 to 30 mm by the addition of fly ash up to 50%.     

Effect of chloride concentration in soil on reinforcement corrosion

This paper presents results of a study conducted to evaluate the effect of chloride concentration in soil on corrosion of reinforcing steel in concrete. Concrete specimens prepared with Type I, Type V and silica fume cements were exposed to soil with a chloride concentration of up to 3%. The effect of chloride concentration in soil on corrosion of reinforcing steel was evaluated by measuring corrosion potentials and corrosion current density. After 18 months of exposure, the concrete specimens were broken and the extent of corrosion of the reinforcing steel was examined and the gravimetric weight loss due to corrosion was assessed. As expected, the degree of corrosion increased with the chloride concentration in the soil. The type of cement also influenced the extent of reinforcement corrosion. For a particular chloride concentration, least reinforcement corrosion was noted in the silica fume cement concrete followed by Type I and Type V cement concrete. Based on the data developed in this study chloride threshold values in soil for the three types of cements investigated are suggested.     

不锈钢钢筋用于混凝土研究

不锈钢材料具有耐腐性能,在海洋性气候和碳、硫化物、氯化物含理较高的环境下的建筑物中,不锈钢钢筋用于混凝土中抵抗腐蚀已引起建筑工程师们的关注。在钢筋混凝土内使用不锈钢钢筋仅是成本有所增加,但结构使用寿命却可大大延长,综合考虑还是很经济的。     

长期暴露混凝土结构中的氯离子侵入研究

根据混凝土中氯离子浓度曲线评价暴露在海洋或道路除冰盐环境下的混凝土结构钢筋腐蚀风险,是一个可靠而有效的方法。对暴露26a的码头和暴露21a的挡浪坝钻取了一批直径100mm的混凝土芯样,同时在实验室制作了三组配合比的混凝土试件进行对比试验。对暴露混凝土的原始资料和环境条件进行了分析,在实验室测定了芯样和试件中的氯离子分布,根据氯离子分布曲线对氯离子扩散系数进行了评价,分析了材料因素和环境因素对氯离子分布的影响。结果表明：实际暴露混凝土中氯离子扩散系数随暴露时间衰减明显;混凝土所处的局部环境造成表层氯离子分布形态有差异;但受混凝土暴露整体环境的影响,混凝土内部氯离子分布则比较一致;混凝土质量差异对氯离子侵入的影响需经过长时间暴露后才能得以反映。图8表8参14     

Influence of detection methods on chloride threshold value for the corrosion of steel reinforcement

The aim of this study is to evaluate the influence of depassivation detection methods on chloride threshold value for the corrosion of steel reinforcement in a concrete. The detection methods of depasstivating steel reinforcement have been examined including electrochemical impedance spectra (EIS), potentiodynamic polarization (PP) in a simulated concrete pore solution and half-cell potential, linear polarization (LP) and electrochemical impedance spectra (EIS) in the concrete contaminated by chloride ions. The results have indicated that in a saturated Ca(OH)₂ solution, the chloride threshold value for the corrosion of steel reinforcement concluded by the potentiodynamic polarization is 0.02 mol/L, which is identical with that decided by EIS. However, in the chloride contaminated concrete, no agreement among the chloride threshold values determined by the three detection methods mentioned above can be found. The range of the values decided by half-cell potential is relatively lower than those by the others, besides, the highest values have been obtained by EIS.     

Rebar corrosion in chloride environment

Chloride induced reinforcement corrosion in concrete is a serious durability problem. Different sources of chloride, i.e. chloride introduced at the fresh stage of concrete (i.e. internal chloride) and chloride entered during the hardened state (i.e. external chloride) may affect the performance of concrete in different ways. For the performance evaluation of reinforced concrete in chloride environment (i.e. both internal and external chloride), there is a need for performing different electrochemical tests to obtain various corrosion parameters that will specify the possibility and the magnitude of corrosion in concrete. In the present study, the results of an experimental investigation that includes different corrosion tests namely potential measurement, corrosion rate measurement and potentiodynamic polarization test have been presented and analyzed to evaluate the performance of concrete both in internal chloride and external chloride exposure conditions. In addition an attempt is made to correlate the corrosion parameters obtained from internal and external chloride exposure conditions. From the results it was observed that, dropped half-cell potential value obtained from external chloride exposure mostly lie in the active zone obtained from internal chloride exposure. In addition it was observed that there was significant difference in corrosion current values obtained from both internal and external chloride exposure conditions. Further on the basis of overall ranking obtained from the results of critical parameters from different exposure conditions, the performance of different cement–steel combinations against chloride induced rebar corrosion has been evaluated.     

Chloride profiles in two marine structures—meaning and some predictions

Interpretations of chloride profiles as well as prediction issues have been two of the more interesting topics when investigating corrosion of concrete structures. Chloride profiles from the oldest concrete pier with stainless steel as reinforcement (Progreso, México) as well as the oldest pretensioned bridge (Maracaibo, Venezuela) have been measured in order to compare penetration mechanisms and to predict future behavior of the whole structures. Some of the results seem to indicate that the penetration mechanism is similar independently of the exposure environment and concrete quality. Besides, these results are compared with a newer construction (a bridge built 17 years ago in USA but exposed to a similar environment as the Progreso pier). The results are discussed in terms of concrete quality, internal amount of chlorides (time of exposure) and environmental variables. Some predictions for maintenance were performed based on the reported chloride thresholds for corrosion onset of black steel and 304 stainless steel. The predictions for both structures were in agreement with the physical and electrochemical evidences, indicating the need of immediate maintenance to avoid further deterioration.     

The importance of chloride content at the concrete surface in assessing the time to corrosion of steel in concrete structures

A literature review in the present study has shown that the chloride ions on the concrete surface exposed to a marine environment including tidal, splash and aerated zones can be accumulated then to increase with time. In order to take this effect into account in a model prediction of the rate of chloride ingresses in concrete, the surface chloride was expressed as a function of time such that (1) constant, (2) linear build-up, (3) square root build-up and (4) square root build-up with an initial set of the surface chloride (a refined model), at a given diffusion coefficient (2 × 10^?12 m²/s). As a result, the constant surface chloride model produced the greatest level of chloride penetration, as an initial set of the surface chloride content was overestimated. The rate of chloride ingresses derived from the highest surface chloride led to the greatest risk of chloride-induced corrosion of steel in concrete, whereas the linear and square root build-up models indicated 2–3 times longer duration of corrosion-free service life. The refinement of a surface chloride build-up suggested a more realistic prediction of chloride profile and corrosion risk, thereby imposing the rate of chloride ingresses between the constant surface chloride, and linear or square root build-up.     

应用人工神经网络预测锈蚀钢筋与混凝土粘结性能

钢筋混凝土粘结强度受多种因素 (如混凝土强度、混凝土保护层厚度、钢筋直径、钢筋类型、钢筋锈蚀率等 )的共同作用 ,建立计算模型比较困难。在试验研究的基础上 ,利用人工神经网络技术 ,分别在考虑单一因素和多种因素的情况下建立BP网络模型预测锈蚀钢筋与混凝土之间的极限粘结力 ,从而不需建立具体的数学模型就可以得到较满意的预测结果。为受腐蚀钢筋混凝土结构力学性能的研究提供一种新方法和新思路 ,为工程实际应用提供简便的预测方法     

混凝土外加剂影响钢筋锈蚀的快测结果剖析

混凝土中的钢筋锈蚀是多种因素引起的,它除了与混凝土密实度、钢筋保护层厚度和钝化膜是否稳定等因素有关外,还与掺入混凝土中的外加剂种类或成分有关。本文用HDV-7晶体带恒电位仪对130多种混凝土外加剂对钢筋锈蚀测试的结果表明,氯盐或含氯盐的混凝土外加剂对钢筋锈蚀的影响较为明显。     

基于锈胀开裂路径的混凝土构件耐久性能概率预测模型及应用

基于混凝土锈胀开裂过程的随机性,提出了一种预测钢筋锈蚀程度、锈胀裂缝开展状况及承载力退化程度时变特性的路径概率模型,并编制了计算程序,能有效评估和预测氯离子侵蚀、混凝土碳化及两者耦合作用环境下钢筋锈蚀状况、锈胀裂缝宽度开展及构件承载力退化程度在不同时段的概率分布,实现了混凝土构件从有害物质侵蚀、钢筋锈蚀、混凝土开裂、钢筋锈蚀加剧、混凝土裂缝宽度增大到构件承载力下降的性能劣化全过程的数值模拟。可预测的性能特征参数包括钢筋样本锈蚀百分比,锈蚀率,混凝土开裂面积百分比,裂缝宽度及构件承载力退化百分比。预测结果与现场检测获得的统计结果吻合良好,验证了该模型的可靠性和有效性。图18表5参18     

混凝土中钢筋的腐蚀行为及腐蚀速率预测

结合理论分析、数值模拟和试验验证,探讨了混凝土中钢筋的腐蚀行为,并建立了钢筋腐蚀速率的预测模型.首先基于试验数据,修正了混凝土的电阻率模型,然后结合混凝土中钢筋腐蚀的电化学原理和宏电池腐蚀模型,分析了保护层厚度、水灰比、氯离子含量和空气相对湿度等因素对钢筋腐蚀过程控制方式和腐蚀速率的影响,并据此建立了混凝土结构钢筋腐蚀速率的预测模型.分析表明,所建立的预测模型能够合理地反映电阻和阴极控制条件下钢筋腐蚀速率的变化趋势,具有较好的预测精度和实用性.     

海工结构服役寿命预测细观数值模拟研究

在现有二维混凝土随机骨料模型基础上,通过引入正态分布随机数来模拟混凝土界面过渡区厚度的非均匀性,并耦合氯离子扩散、钢筋锈蚀和混凝土损伤,建立了海工结构服役寿命预测细观数值模型.研究表明:由氯离子扩散引起的单根钢筋非均匀锈蚀导致混凝土保护层形成3条主裂缝,3条主裂缝之间夹角约为120°,出现这种现象的主要原因是界面过渡区加速了氯离子扩散,次要原因是界面过渡区的力学性能劣化;在相同钢筋锈蚀量条件下,非均匀锈蚀钢筋混凝土比均匀锈蚀钢筋混凝土的服役年限短,混凝土保护层开裂形态也不一样;数值模拟的氯离子含量分布、裂缝形态与试验数据较为吻合,验证了所建立的数值模型的可靠性.     

Life-cycle cost analysis of reinforced concrete structures in marine environments

Chloride-induced corrosion of carbon steel reinforcement is the main cause of deterioration of reinforced concrete (RC) structures in marine environments. One of the ways to protect RC structures from corrosion is to use corrosion-resistant stainless steel reinforcing bars. However, stainless steel is between six and nine times more expensive than carbon steel. Thus, its use can only be justified on a life-cycle cost basis. In the paper a time-variant probabilistic model was presented to predict expected costs of repair and replacement which was then used to calculate life-cycle costs for RC structures in marine environments under different exposure conditions. Results of the life-cycle cost analysis can be applied to select optimal strategies improving durability of RC structures in marine environments, including the use of stainless steel reinforcement.     

氯离子侵蚀效应对RC桥墩抗震性能的影响

为研究混凝土桥梁结构在服役期内由于环境氯离子侵蚀效应引起钢筋、混凝土锈蚀退化等导致结构抗震性能退化的规律,以某多跨钢筋混凝土连续梁桥为例,采用OpenSees软件建立非线性动力分析模型,根据已有研究成果并基于概率方法研究了墩柱截面主筋和箍筋锈蚀的开始时间和锈蚀率大小,进而建立了钢筋的直径及屈服强度退化模型;针对考虑纵筋锈蚀、考虑箍筋锈蚀、同时考虑纵筋和箍筋锈蚀3种情况,分别分析了材料退化对桥墩抗震性能的影响。结果表明:同等条件下箍筋锈蚀比纵筋锈蚀更早;随着时间的推移,氯离子侵蚀效应会导致桥墩抗震能力下降,结构的抗震需求明显增加;与以往只考虑纵筋锈蚀的情况相比,同时考虑箍筋和纵筋锈蚀时桥墩抗震性能退化更严重。     

Novel hybrid models of ANFIS and metaheuristic optimizations (SCE and ABC) for prediction of compressive strength of concrete using rebound hammer field test

In this study, we developed novel hybrid models namely Adaptive Neuro Fuzzy Inference System (ANFIS) optimized by Shuffled Complex Evolution (SCE) on the one hand and ANFIS with Artificial Bee Colony (ABC) on the other hand. These were used to predict compressive strength (Cs) of concrete relating to thirteen concrete-strength affecting parameters which are easy to determine in the laboratory. Field and laboratory tests data of 108 structural elements of 18 concrete bridges of the Ha Long-Van Don Expressway, Vietnam were considered. The dataset was randomly divided into a 70:30 ratio, for training (70%) and testing (30%) of the hybrid models. Performance of the developed fuzzy metaheuristic models was evaluated using standard statistical metrics: Correlation Coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results showed that both of the novel models depict close agreement between experimental and predicted results. However, the ANFIS-ABC model reflected better convergence of the results and better performance compared to that of ANFIS-SCE in the prediction of the concrete Cs. Thus, the ANFIS-ABC model can be used for the quick and accurate estimation of compressive strength of concrete based on easily determined parameters for the design of civil engineering structures including bridges.     

混凝土中钢筋腐蚀监测传感器的试验

对一种混凝土中预埋式梯形阳极传感器进行介绍,通过测量传感器中阳极的电位及其与阴极之间的宏电流,监测混凝土中的钢筋在含氯环境下的腐蚀危险性随时间变化的情况。实验室的测试表明,该梯形阳极传感器可较好地判断临界氯离子浓度侵入混凝土中的深度,从而可以提前判断钢筋腐蚀的危险性。     

混凝土构件中钢筋锈蚀的中子断层扫描成像

制备了小型混凝土构件,通过三点弯曲诱导裂缝和氯盐溶液干湿循环加速其中钢筋锈蚀,采用自然电位法监测钢筋的腐蚀电位,并采用中子断层扫描成像技术对钢筋锈蚀产物分布进行了分析.结果表明:钢筋混凝土构件经过85次氯盐溶液干湿循环后,采用中子断层扫描成像技术对其进行三维扫描成像,可直观呈现钢筋锈蚀产物分布状况;钢筋锈蚀产物集中分布于裂缝断面钢筋与基体界面的底部区域,并沿界面逐渐向外扩展,符合氯盐诱导钢筋锈蚀的坑蚀规律.这为研究混凝土结构中钢筋的锈蚀机理提供了一种新的试验方法.