Predicted Failure Loads Research Articles

Machine Learning for Analyzing Concrete Cover Separation in Externally Bonded FRP RC Beams

Strengthening of concrete structures with Externally Bonded (EB) Fiber Reinforced Polymer (FRP) is one the most cost effective, efficient, and sustainable rehabilitation techniques. However, usually the ultimate tensile strength of the FRP cannot be achieved due to the premature debonding of the FRP or delamination of the concrete cover. In this last case, known as concrete cover separation (CCS), high stress concentration at the free end of FRP laminate, in combination with the shear stress at that section, cause the initiation of a shear crack that, if not controlled by the shear reinforcement, propagates in concrete just below internal reinforcement. Various analytical and empirical models have been developed to predict this phenomenon but none of them could give a failure load with reasonable accuracy. On the other hand, Machine Learning (ML) has been proved very effective in predicting behaviors that are difficult to quantify using mechanics.This paper explores ML algorithms to predict the failure load of flexural elements that undergo CCS. To this end, a database has been collected that comprises 140 four-point bending tests on beams reinforced with EB CFRP that failed by CCS. K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBOOST) algorithms have been applied and then ranked based on their R-squared score. R-squared scores obtained from ML are the highest compared to the analytical models described in this paper. Moreover, the mean values and standard deviation of the ratio of experimental failure load and that of calculated by the ML model are the lowest compared to the analytical models. The predictions from the ML models are found more aligned with the experimental results than the analytical models. KNN is chosen as the best ML algorithm for the prediction of failure load with an R-squared score of 0.97.

Resultados experimentais e análise de carga limite pelo Método de Bielas e Tirantes (MBT) de vigas-parede com entalhes e aberturas

Abstract This article presents experimental results of eight non-aligned, non-geometrically symmetrical deep beams with notches and openings. The variables considered in the study were the presence of web reinforcement, and the geometry of the deep beams. Along with the experimental investigation, a study of strut-and-tie models (STM) representing the behavior (failure mode and maximum load) of reinforced concrete deep beams with complex geometries was performed. The experimental results showed that the ultimate load capacity of deep beams is significantly affected by the presence of reinforcement in the web. Furthermore, the study showed that the STM is conservative and tends to underestimate the results, reducing its ability to predict failure load.

Testing, numerical modelling and design of G550 high strength cold-formed steel built-up section columns

This paper investigates the buckling behaviour and load-carrying capacity of G550 high strength cold-formed steel built-up section columns under axial compression through experiments and numerical simulations. Two types of built-up sectional profiles were formed, which were defined as built-up OI-section and built-up CB-section. Each built-up OI-section member is formed by connecting two cold-formed steel C-section members in a back-to-back manner using self-drilling screws, while each built-up CB-section member consists of a cold-formed steel C-section member and a cold-formed steel U-section member, which are connected in a face-to-face manner by self-drilling screws. The experimental programme included tensile coupon tests, initial geometric imperfection measurements and 20 pin-ended column compression tests. In the numerical modelling programme, finite element models were developed and validated against the experimental results, and then used for parametric analyses to generate a total of 250 numerical data with different cross-section dimensions and member lengths. Based on the experimental and numerical data, the accuracy of both the effective width method and the direct strength method for predicting the strengths of G550 high strength cold-formed steel built-up section columns, as set out in the American Specification, was evaluated. The evaluation results indicated that both the effective width method and direct strength method provided accurate and consistent failure load predictions for G550 high strength cold-formed steel built-up OI-section columns on average, but with some unsafe failure load predictions, while the predicted failure loads were inaccurate, scattered and conservative for G550 high strength cold-formed steel built-up CB-section columns. Moreover, the effective width method and direct strength method yielded a similar level of design consistency for G550 cold-formed steel built-up section columns, but the direct strength method resulted in more accurate and less conservative failure load predictions than the effective width method. The modifications to the codified DSM equations were proposed for G550 high strength cold-formed steel built-up section columns and shown to provide improved predictions of failure load over the design codes.

Structural behaviour and resistances of high strength concrete-filled stainless steel tube (HCFSST) beam-columns

This paper reports experimental and numerical investigations into the structural behaviour and resistances of high strength concrete-filled stainless steel tube (HCFSST) beam-columns under combined compression and bending. An experimental investigation was conducted on sixteen HCFSST beam-columns specimens fabricated from stainless steel tubes with two cross-section sizes and high strength concretes with four material grades, and included concrete cylinder tests, tensile coupon tests, initial global geometric imperfection measurements and eccentric compression tests. The test setups and procedures were fully reported and the experimental observations were discussed and analysed in detail. It was found that the plane cross-section assumption was valid for eccentrically loaded HCFSST sections and the lateral deflection distribution patterns for HCFSST beam-columns were approximately half-sine wave shapes. The test results were used in a subsequent numerical investigation for the validation of finite element models, which were then employed to conduct parametric studies to generate additional numerical data over a wide range of cross-section dimensions, member lengths and loading combinations. Based on the experimental and numerical results, the relevant design rules, as set out in the European code, American specification and Australian/New Zealand standard, were evaluated for their applicability to HCFSST beam-columns. The evaluation results revealed that the European code provided accurate but scattered failure load predictions when used for HCFSST beam-columns, while the American specification and Australian/New Zealand standard resulted in conservative and scattered failure load predictions.

Prediction of last ply failure load of keyhole notched laminated composites using the virtual isotropic material concept

Composite laminates have become increasingly popular in industries like aerospace and shipbuilding. In practical applications, the creation of notches in composite laminates is often necessary to enable assembly and modifications. This rise in the use of notched composite laminates highlights the need for reliable methods to predict potential failures in these components. With these predictions, the safety and reliability of composite structures can be ensured by preventing catastrophic failures. The present paper investigates the use of the Virtual Isotropic Material Concept (VIMC) combined with the Finite Fracture Mechanics (FFM) criterion to predict the Last Ply Failure (LPF) load in keyhole notched composite laminates and under mode I loading conditions. Experimental tests were conducted to measure the LPF load of E-glass/Epoxy keyhole notched specimens, and the results were compared with the predicted results using the VIMC-FFM criterion. The paper also derives an expression for the Stress Intensity Factor (SIF) function for a crack that emanates from the keyhole notch tip under mode I loading conditions. The derived equation matches very well with numerical data and have a mean absolute error about 2% in the studied domain. The study shows that the VIMC-FFM criterion predicts the LPF load of keyhole notched composite laminates with acceptable accuracy and in a simple and low-cost manner.

The effect of deep learning-based lesion segmentation on failure load calculations of metastatic femurs using finite element analysis

Bone ranks as the third most frequent tissue affected by cancer metastases, following the lung and liver. Bone metastases are often painful and may result in pathological fracture, which is a major cause of morbidity and mortality in cancer patients. To quantify fracture risk, finite element (FE) analysis has shown to be a promising tool, but metastatic lesions are typically not specifically segmented and therefore their mechanical properties may not be represented adequately. Deep learning methods potentially provide the opportunity to automatically segment these lesions and change the mechanical properties more adequately. In this study, our primary focus was to gain insight into the performance of an automatic segmentation algorithm for femoral metastatic lesions using deep learning methods and the subsequent effects on FE outcomes. The aims were to determine the similarity between manual segmentation and automatic segmentation; the differences in predicted failure load between FE models with automatically segmented osteolytic and mixed lesions and the models with CT-based lesion values (the gold standard); and the effect on the BOne Strength (BOS) score (failure load adjusted for body weight) and subsequent fracture risk assessments.From two patient cohorts, a total number of 50 femurs with osteolytic and mixed metastatic lesions were included in this study. The femurs were segmented from CT images and transferred into FE meshes. The material behavior was implemented as non-linear isotropic. These FE models were considered as gold standard (Finite Element no Segmented Lesion: FE-no-SL), whereby the local calcium equivalent density of both femur and metastatic lesion was extracted from CT-values. Lesions in the femur were manually segmented by two biomechanical experts after which final lesion segmentation for each femur was obtained based on consensus of opinions between two observers. Subsequently, a self-configuring variant of the popular deep learning model U-Net known as nnU-Net was used to automatically segment metastatic lesions within the femur. For these models with segmented lesions (Finite Element with Segmented Lesion: FE-with-SL), the calcium equivalent density within the metastatic lesions was set to zero after being segmented by the neural network, simulating absence of load-bearing capacity of these lesions. The models (either with or without automatically segmented lesions) were loaded incrementally in axial direction until failure was simulated. Dice coefficient was used to evaluate the similarity of the manual and automatic segmentation. Mean calcium equivalent density values within the automatically segmented lesions were calculated. Failure loads and patterns were determined. Furthermore, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for both groups by comparing the predictions to the occurrence or absence of actual fracture within the patient cohorts.The automatic segmentation algorithm performed in a none-robust manner. Dice coefficients describing the similarity between consented manual and automatic segmentations were relatively low (mean 0.45 ± standard deviation 0.33, median 0.54). Failure load difference between the FE-no-SL and FE-with-SL groups varied from 0 % to 48 % (mean 6.6 %). Correlation analysis of failure loads between the two groups showed a strong relationship (R2 > 0.9). From the 50 cases, four cases showed clear deviations for which models with automatic lesion segmentation (FE-with-SL) showed considerably lower failure loads. In the whole database including osteolytic and mixed lesions, sensitivity and NPV remained the same, but specificity and PPV decreased from 94 % to 83 %, and from 78 % to 54 % respectively from FE-no-SL to FE-with-SL.This study indicates that the nnU-Net yielded none-robust outcomes in femoral lesion segmentation and that other segmentation algorithms should be considered. However, the difference in failure pattern and failure load between FE models with automatically segmented osteolytic and mixed lesions were relatively small in most cases with a few exceptions. On the other hand, the accuracy of fracture risk assessment using the BOS score was lower compared to the FE-no-SL. In conclusion, this study showed that automatic lesion segmentation is a none-solved issue and therefore, quantifying lesion characteristics and the subsequent effect on the fracture risk using deep learning will remain challenging.

Acoustic emission-based failure load prediction for plain woven laminates under quasi-static indentation

Composites are widely used in engineering applications, and their penetration resistance is critical for performance and safety. However, testing the failure load of composites directly leads to component failure, making it challenging to evaluate the expected residual capacity. To address this issue, this study proposes an artificial neural network (ANN) method that accurately predicts the penetration failure load of composites using acoustic emission (AE) data. A cyclic loading test schedule is designed to capture the AE data during each cycle, and a relationship between AE data and load ratio (LR) is established. To predict the failure load, an extrapolation method (EM) based on uncertainty is proposed in this paper. This approach enables the prediction of failure load intervals when LR equals 1, with relative errors of less than 7.66%. In cases where multiple loads are not feasible, the single-point prediction method (SPM) can be used instead of the extrapolation method. However, it is crucial to avoid training AE data during the initial loading stage for accurate predictions. This study recommends a loading ratio of more than 0.1 for optimal results with this approach.

Performance of rubberized reinforced concrete columns at ambient and high temperatures

The proliferation of discarded rubber tires is rapidly increasing at a concerning pace. Driven by the significant movement towards promoting environmental sustainability and mitigating the adverse environmental impact associated with non-biodegradable waste rubber tires, the objective of this study is to identify a viable and ecologically responsible resolution to the issue of discarded tires. This study experimentally focuses on the structural response and load-carrying capacity of reinforced concrete (RC) short columns containing crumb rubber as a partial replacement for fine aggregate after being exposed to temperatures of 27 °C, 300 °C, and 500 °C. Four concrete mixes were produced in which the natural fine aggregate (NFA) was partially replaced by CR with ratios of 0%, 5%, 10%, and 20% in volume. Twelve columns (three columns from each mix) were cast and tested under concentric loading. The experimental results showed that the workability and compressive strength of the concrete mixes decreased with increasing the CR replacement ratio. The residual failure load of columns decreased with increasing CR quantities and heating temperatures. The CR quantity had a more considerable impact on the decline of the column capacity than the heating temperatures. Analytical equations from international standards ACI 318–14, CSA A23.3, and previously existing equations were applied to study the validity of these equations in predicting the failure load of heated rubberized RC columns. Finally, a proposed equation for predicting the failure load of the columns is developed. The predicted failure loads obtained from the proposed equation were compared to the experimental results. The predictions from the proposed equation were in good agreement with the experimental data. Different statistical tests were done to compare the predictions from the proposed equation and previously existing equations for predicting the failure load of heated rubberized RC columns.

Testing, numerical modelling and design of S890 and S960 ultra-high strength steel circular hollow sections under combined loading

The present paper reports the experimental and numerical investigations into the structural behavior and resistances of S890 and S960 ultra-high strength steel circular hollow sections (CHS) under combined loading. The experimental investigation was performed firstly, comprising the tensile coupon tests on S890 and S960 ultra-high strength steel materials, precise measurements of initial local geometric imperfections and eccentrically loaded tests on 12 stub columns, with each 6 respectively conducted on S890 and S960 ultra-high strength steel CHS. The numerical investigation was subsequently conducted, where numerical models were created and verified against the experimental responses and adopted to conduct parametric studies to produce more numerical data over an extensive variety of loading combinations and cross-section geometries. The design interaction curves, as codified in the European, Australian and American standards, were assessed for their applicability, based on the numerical and test data, to S890 and S960 ultra-high strength steel CHS under combined loading. The evaluation findings demonstrated that (i) the European code leads to the slightly conservative failure load predictions for Class 1 (and 2) S890 and S960 ultra-high strength steel CHS under combined loading, but overly conservative predictions for Class 3 and 4 counterparts, (ii) the predicted failure loads by American specification for non-compact (i.e. Class 3 and 4) are more accurate due to the more precise compression and bending end points and (iii) the resistance predictions by Australian standard for compact (i.e. Class 1 and 2) sections are rather conservative due mainly to its inaccurate design interaction curve.

Stainless steel built-up section stub columns: Testing, numerical modelling and design

This paper presents experimental and numerical investigations into the cross-sectional compressive behaviour and resistances of stainless steel built-up section stub columns. An experimental programme was firstly conducted on six built-up (open) I-sections and seven built-up (closed) tubular sections, with each composed of two identical press-braked stainless steel channel sections assembled by self-tapping screws, and included tensile coupon tests, initial local geometric imperfection measurements and twenty stub column tests. The experimental programme was followed by a numerical modelling programme, where finite element models were developed and validated against test results and then used to conduct parametric studies, aiming at investigating the effect of screw spacings and generating further numerical data over a wide range of cross-section dimensions. For the design of a stainless steel built-up section stub column, the current European code and American specification treat it as two individual channel section members and adopt effective width methods for calculating the cross-section compression resistance of each channel section member. Both design codes were found to result in many unsafe failure load predictions for stainless steel built-up I-section stub columns but conservative failure load predictions for stainless steel built-up tubular section stub columns. Finally, revised codified design rules were proposed by treating each built-up section as a whole and using an equivalent thickness of the overlapped plate elements, and shown to provide accurate, consistent and safe cross-section compression predictions for stainless steel built-up section stub columns.

Unified machine-learning-assisted design of stainless steel bolted connections

For the design of stainless steel bolted connections, current design codes firstly calculate the design resistance of each potential failure mode and then take the minimum of the design resistances calculated from all the potential failure modes as the final design failure load. However, this design framework has been found to be tedious and also leads to inaccurate failure load predictions. In this paper, a more accurate and unified predictive framework for stainless steel bolted connections made of different materials with various configurations and bolt hole patterns at both room and elevated temperatures is proposed based on machine learning. This paper starts with a collection of 301 experimental data of stainless steel bolted connections to establish a database. Then, regression models for failure load predictions were developed and trained by six machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, Adaptive Boosting, Extreme Gradient Boosting and Cat Boosting, with the key hyperparameters for each machine learning algorithm tuned. This is followed by the evaluation of the model performance by means of a series of statistical indices, with the results indicating that the regression model trained by Support Vector Machine has the best model performance. On the basis of the collected experimental data, the regression model trained by Support Vector Machine and current design codes were assessed and compared, showing that the current design codes are rather inaccurate, while the machine-learning-assisted design method is a unified method and can provide accurate and consistent failure load predictions for stainless steel bolted connections made of different materials with various configurations and bolt hole patterns at both ambient and elevated temperatures.

Machine learning techniques for prediction of failure loads and fracture characteristics of high and ultra-high strength concrete beams

Machine learning techniques for prediction of failure loads and fracture characteristics of high and ultra-high strength concrete beams

Modeling the fracture behavior of 3D-printed PLA as a laminate composite: Influence of printing parameters on failure and mechanical properties

Additively Manufactured parts are known to be heavily affected by the 3D-printing parameters, and their layered morphology represents a challenge in the mechanical design analysis for engineering applications. In this work, the fracture mechanics of 3D-printed polylactic acid (PLA) samples along different printing directions was simulated as a laminate composite using different numerical approaches, i.e. extended Finite Element (XFEM) and cohesive method. Tensile specimens were 3D-printed via Fused Filament Fabrication in different directions and tested to build the stiffness matrix needed to define the constitutive behavior of the 3D-printed material. Moreover, the influence of different printing parameters (i.e. printing direction, infill, nozzle temperature and perimeter) on the mechanical response was investigated using the statistical approach analysis of variance (Anova). The statistical analysis has shown a strong influence of the printing direction and the perimeters on the resulting mechanical properties, with tensile strength ranging from 52 MPa in the best case to 4 MPa in the worst. The performed FEM analysis correctly predicts the fracture behavior of the 3D-printed samples, with an error on the predicted failure load well below 7%. The investigated model, thus, represents a useful analysis approach to broader the use of 3D printing in engineering applications.

Fracture Load Prediction of Non-Linear Structural Steels through Calibration of the ASED Criterion

In this work, the application of the Average Strain Energy Density (ASED) criterion for the estimation of failure loads in materials with nonlinear behavior containing U-shaped notches is presented. The ASED criterion was originally defined to predict failure in the presence of notches in materials with linear-elastic behavior. However, most structural materials (e.g., ferritic-pearlitic steels) can develop non-linear behavior (e.g., elastoplastic). In this sense, this work proposes to extend the use of the ASED criterion to materials that exhibit plasticity by a thorough calibration of their characteristic parameters, and the subsequent extrapolation of the liner-elastic formulation of the ASED criterion to non-linear situations. To validate this methodology, a wide range of structural steels (S275JR, S355J2, S460M, and S690Q) were used operating in the ductile-to-brittle transition range, with six different notch radii (0 mm, 0.15 mm, 0.25 mm, 0.50 mm, 1.0 mm, and 2.0 mm). The results obtained demonstrate that the proposed calibration of the ASED criterion allows for accurate predictions of failure loads. Therefore, it is shown that, for the notch radii analyzed in this work and for testing temperatures within the material ductile-to-brittle transition range, it is possible to extrapolate the ASED criterion to obtain estimates of failure loads in materials with U-shaped notches that exhibit ductile behavior.

Prediction of failure load in flat-joggle-flat co-cured composite joints using artificial neural networks

The current research examines the impact of bonding angle, bonding width, and adherend thickness on the failure load of flat-joggle-flat (FJF) co-cured composite joints. The primary goal of this work is to use an artificial neural network (ANN) to predict the failure load at the FJF joint. The experimental data was fed into the network, and the Colab tool was used to design and train the ANN network using a back-propagation algorithm. Experimental results revealed that, 8 mm to 12 mm adherend thickness, 25 mm adherend width, and a 10° to 15° bonding angle, gave maximum failure load. The ANN model estimated the predictive failure load with acceptable error. The results obtained from ANN, R2= 0.9803 for training andR2 = 0.9242 for testing the data, are within the acceptable error, so the experimental and ANN results are consistent and in good agreement.

First-ply failure load prediction of delaminated pre-twisted rotating composite conical shells

First-ply failure load prediction of delaminated pre-twisted rotating composite conical shells

Forecasting failure load of Sandstone under different Freezing-Thawing cycles using Gaussian process regression method and grey wolf optimization algorithm

The stability analysis of rock is an important basis to ensure the safe exploitation of underground resources and the reliable operation of space engineering. Failure load is one of the most important parameters on which the stability analysis of rocks can be performed. Rocks are constantly subjected to the freezing-thawing (F-T) weathering phenomena. F-T cycles can significantly affect the failure load of rocks and cause geological disasters in cold regions. As a result, the effects of F-T cycles on rock mechanical characteristics should be carefully investigated. Weak, heavily fractured, worn, and thinly bedded rocks, on the other hand, can never provide enough high-quality cores. Aside from being difficult, time-consuming, and costly, this test also entails destructive testing. Therefore, the prediction of failure load under different F-T cycles utilizing simplified indirect test procedures has been emphasized. In this study, a Gaussian process regression (GPR) technique was developed to predict the failure load of rock samples, utilizing 300 datasets obtained from the laboratory tests for Sandstone under different F-T cycles (0,1,4,8,16,32). Seven input parameters effective on the failure load were considered in the datasets. The grey wolf optimization (GWO) algorithm was used to fine-tune the GPR’s hyperparameters. The evaluation indices results showed that the GPR model developed by this study has a high potential ability in the prediction of failure load. The stepwise method was used for feature selection purposes. Confining pressure and porosity parameters were selected as the most effective features on the failure load. Considering only the confining pressure and porosity parameters in the model, the accuracy of the model was increased as the RMSE and R2 were obtained by about 5.57 and 0.9885, respectively. Also, the performance of the GPR model was compared to the other machine learning methods. Finally, the GPR model was recommended to predict the failure load of rock samples. This work’s significance is that it allows geotechnical engineers to accurately estimate the failure load rock samples under F-T cycles. In this way, instead of preparing more samples and waiting a long time to prepare these samples for the same laboratory test, we can use the trained model and minimize the time and costs required for laboratory tests.

Predicting Failure of Additively Manufactured Specimens with Holes

Experimental and computational studies were conducted to predict failure loads of specimens containing different-sized holes made using the additive manufacturing (AM) technique. Two different types of test specimens were prepared. Flat specimens, manufactured from polylactic acid (PLA), were subjected to uniaxial loading. Tubular specimens, made of polycarbonate (PC), were subjected to combined loading that was applied using uniaxial testing equipment. Test specimens were uniquely designed and printed to apply the combined bending and torsional loads to tubular specimens. A newly developed failure theory was applied to predict the loads that would result in the fracture of these test specimens. This theory is composed of two conditions related to stress and the stress gradient to be simultaneously satisfied to predict failure. The failure loads predicted using the new failure criteria were compared closely with the experimental data for all test specimens. In addition, a semi-empirical equation was developed to predict the critical failure surface energy for different printing angles. The critical failure surface energy is a material property and is used for the stress gradient condition. Using the semi-empirically determined values for the failure criterion provided close agreement with experimental results.

Ferritic stainless steel thin sheet bolted connections failing by bearing–curling interaction: Testing, modelling and design

This paper presents experimental and numerical studies of ferritic stainless steel thin sheet bolted connections failing by bearing–curling interaction. An experimental programme was firstly conducted on fifteen ferritic stainless steel thin sheet bolted connection specimens, including eleven specimens designed with curling and four specimens designed without curling. The test setup and procedures as well as the key test results, including failure loads, failure modes, load–in-plane elongation curves and load–out-of-plane deformation curves, were reported. Following the experimental programme, a numerical modelling programme was performed, where finite element models were developed and validated against the test results and then used to perform parametric studies to generate further numerical data. Based on the obtained numerical data, the effects of various geometric parameters, including end distances, edge distances, longitudinal spacings and sheet thicknesses, on failure loads of ferritic stainless steel thin sheet bolted connections were discussed. Both the test and numerical data were then used to assess the codified design rules for ferritic stainless steel thin sheet bolted connections susceptible to bearing–curling interaction, as set out in the European code and American specification. On the basis of the assessment results, the European code and American specification were found to respectively underestimate the actual load-carrying capacities by 57% and 18%, on average. Besides, a relevant design method proposed for carbon steel thin sheet bolted connections was assessed for its applicability to ferritic stainless steel thin sheet bolted connections, with the results showing that it provided more consistent failure load predictions than the design codes, but the predicted failure loads were still conservative. Therefore, a revised design formula was proposed and shown to provide improved failure load predictions.

Quantitative MRI Biomarkers to Predict Risk of Reinjury Within 2 Years After Bridge-Enhanced ACL Restoration

Background: Quantitative magnetic resonance imaging (qMRI) methods were developed to establish the integrity of healing anterior cruciate ligaments (ACLs) and grafts. Whether qMRI variables predict risk of reinjury is unknown. Purpose: To determine if qMRI measures at 6 to 9 months after bridge-enhanced ACL restoration (BEAR) can predict the risk of revision surgery within 2 years of the index procedure. Study Design: Cohort study; Level of evidence, 2. Methods: Originally, 124 patients underwent ACL restoration as part of the BEAR I, BEAR II, and BEAR III prospective trials and had consented to undergo an MRI of the surgical knee 6 to 9 months after surgery. Only 1 participant was lost to follow-up, and 4 did not undergo MRI, leaving a total of 119 patients for this study. qMRI techniques were used to determine the mean cross-sectional area; normalized signal intensity; and a qMRI-based predicted failure load, which was calculated using a prespecified equation based on cross-sectional area and normalized signal intensity. Patient-reported outcomes (International Knee Documentation Committee subjective score), clinical measures (hamstring strength, quadriceps strength, and side-to-side knee laxity), and functional outcomes (single-leg hop) were also measured at 6 to 9 months after surgery. Univariate and multivariable analyses were performed to determine the odds ratios (ORs) for revision surgery based on the qMRI and non-imaging variables. Patient age and medial posterior tibial slope values were included as covariates. Results: In total, 119 patients (97%), with a median age of 17.6 years, underwent MRI between 6 and 9 months postoperatively. Sixteen of 119 patients (13%) required revision ACL surgery. In univariate analyses, higher International Knee Documentation Committee subjective score at 6 to 9 months postoperatively (OR = 1.66 per 10-point increase; P = .035) and lower qMRI-based predicted failure load (OR = 0.66 per 100-N increase; P = .014) were associated with increased risk of revision surgery. In the multivariable model, when adjusted for age and posterior tibial slope, the qMRI-based predicted failure load was the only significant predictor of revision surgery (OR = 0.71 per 100 N; P = .044). Conclusion: Quantitative MRI-based predicted failure load of the healing ACL was a significant predictor of the risk of revision within 2 years after BEAR surgery. The current findings highlight the potential utility of early qMRI in the postoperative management of patients undergoing the BEAR procedure.