News Detail

The Concrete Industry in the Era of Artificial Intelligence

2/15/2021

Register Now »

The ACI Virtual Concrete Convention – known as the world’s gathering place for advancing concrete – will be held virtually from March 28-April 1, 2021, and will feature 45 total sessions. All attendees will be provided the opportunity to advance their knowledge and earn Continuing Education Units (CEUs)/Professional Development Hours (PDHs). The featured session titled The Concrete Industry in the Era of Artificial Intelligence is moderated by M.Z. Naser, and will provide insight on the merit of using artificial intelligence (AI) in the concrete industry with focus on how to better the performance of concrete materials at ambient and elevated temperatures and showcase the substantial potential of using AI to improve design of concrete structures under traditional and fire conditions. This featured session is sponsored by Advancing Organizational Excellence (AOE).

Presentations Include:

1. Machine Learning Applications in Structural Engineering: Hope, Hype or Hindrance?
   Speaker(s): Henry Burton
   The recent success of machine learning (ML) applications in areas such as bioengineering, medicine, and advertising has been highly visible. This has created a domino effect where others have begun to ask whether their respective fields of practice, including structural engineering, can be transformed or “revolutionized” by ML. This presentation will cover the areas of current and potential machine learning applications in structural engineering while placing them into three categories: (1) improving the predictive accuracy of existing empirical/statistical models used in structural engineering practice (e.g., empirical drift capacity models for concrete shear walls), (2) increasing the efficiency of long-standing structural engineering tasks (e.g. performance-based seismic design) and (3) solving problems that, without the use of ML, would be otherwise intractable (e.g., near real-time post-earthquake damage assessment). The challenges and opportunities associated with utilizing ML within these three contexts will be interwoven into the discussion. The presentation will conclude with some strategies on how the community can proceed with a “cautious exploration” of the usefulness of ML to our field.
   
   
2. The Use of Machine Learning Algorithms and IoT Sensor Data for Concrete Performance Testing and Analysis
   Speaker(s): Andrew Fahim, Pouria Ghods, Aali Alizadeh, and Tahmid Medhi
   With IoT sensors gaining widespread adoption in recent years for monitoring in-situ concrete properties, the volume of data generated using these sensors is growing at a significant rate. These sensors are typically used for several purposes among which temperature, humidity, and strength monitoring (using the maturity method) are currently the most common. This data is typically collected at centralized cloud-based databases where they can be accessed by end-users as well as algorithm developers. This presentation will cover how data from these IoT sensors has been used by the authors to train machine learning algorithms to perform several tasks including but not limited to: detecting anomalies, detecting events in the service-life of the sensor (e.g. concrete pouring,) suggesting mixture alterations to optimize performance and predicting future performance. These capabilities are currently being used by concrete practitioners on daily basis. This is done using data collected from tens of thousands of sensors, used in over 7000 projects representing geographical regions of over 50 countries and representing several thousand unique concrete mixtures. This, to the authors’ knowledge, is the largest dataset available for training such algorithms. Challenges in maintaining this ever-growing dataset as well as opportunities with the growing capabilities of these algorithms are presented.
   
   
3. Damage Detection in Concrete Bridge T Girders Using 3-D Finite Element Simulations Trained by Artificial Neural Network
   Speaker(s): Hayder Rasheed, Alaaeldin Abouelleil, and Eric Fletcher
   The structural deterioration of aging infrastructure systems is becoming an increasingly important issue worldwide. To compound the problem, economic strains limit the resources available for repair or replacement of such systems. Over the past several decades, structural health monitoring (SHM) has proven to be a cost-effective method for the detection and evaluation of damage in structures. Visual inspection and condition rating are one of the most commonly applied SHM techniques, but the effectiveness of SHM varies depending on the availability and experience of qualified personnel and largely qualitative damage evaluations.Simply supported three-dimensional reinforced concrete T-beams with varying geometric, material, and cracking properties were modeled using Abaqus finite element (FE) analysis software. Up to five cracks were considered in each beam, and the ratios of stiffness between cracked and healthy beams with the same geometric and material parameters were measured at nine equidistant nodes along the beam. A feedforward ANN utilizing backpropagation learning algorithms was then trained on the FE model database with beam properties and nodal stiffness ratios serving as inputs for the neural network model. The outputs consisted of the predicted parameters of location, depth, and width of up to five cracks. This inverse problem is very difficult or impossible to solve with the training done by the Artificial Neural Network. One ANN was trained to predict the parameters of the cracks using the full database of FE simulations. The damage prediction ANN achieved fair prediction accuracies, with coefficients of determination (R2) equal to 0.42. This result was the outcome of the no uniqueness in the prediction of this inverse analysis. Nevertheless, this ANN model provides a rough estimate of the cracking type and damage content in bridge girders once the nodal stiffness ratios are measured or estimated.
   
   
4. The Power of Statistical Learning Applied to the Proportioning of Fiber-Reinforced Concrete Mixes
   Speaker(s): Emilio Taenqua
   Fiber-reinforced concrete (FRC) presents flexural load-bearing capacity in the cracked state, and residual flexural strength parameters are the basis of the material’s characterization and specification, together with compressive strength. However, the incorporation of fibers also affects the workability of the fresh mix. The correlations between these parameters and the dosage, size, and type of fibers as well as the relative amounts of the other constituents in a FRC mix are usually described separately for different specific mixes, with limited general validity. Furthermore, residual flexural strength parameters are mutually interdependent, and therefore conventional approaches that regard them as independent variables fail to make the most of the information which extracted from characterization tests results. The project “Optimization of Fiber-Reinforced Concrete using Data Mining” (abbreviated as OptiFRC), funded by the Concrete Research Council / ACI Foundation, has undertaken the first meta-analysis of FRC mixes and their main properties. An exhaustive database comprising nearly 2,000 cases of FRC mixes and their properties has been compiled from papers published in indexed journals. All this information has been analyzed from a data analytics perspective in order to develop statistical models for the multi-objective optimization of FRC mix designs. Semi-empirical equations have been obtained to relate residual flexural strength, compressive strength, and slump to the FRC mix proportioning, not only in terms of average values but also to account for their variability and sensitivity to changes.
   
   
5. State of the Art on Self-healing Capacity of Cementitious Materials Based on Data Mining Strategies
   Speaker(s): Liberato Ferrara, Ali Al-Obaidi, and S. Gupta
   Concrete and cement-based materials inherently possess an autogenous self-healing capacity, which is even high in High and Ultra High Performance Concretes (HPC, UHPC) because of the high cement and supplementary cementitious materials (SCM) and low water/binder ratios. Despite the huge amount of literature on the topic self-healing concepts still fail to consistently enter into design strategies able to effectively quantify their benefits of the structural performance. In this study, quantitative relationships through statistical models have been carried out. The employed approaches aimed at establishing a correlation between the mix proportions, mainly in terms of quantity and type of binders, exposure type, and time and width of the initial crack against suitably defined self-healing indices, quantifying the recovery of material performances which can be of interest for intended applications. Therefore, this study provides, for the first time in the literature to the authors’ knowledge, a holistic investigation on the autogenous self-healing capacity of cement-based materials based on extensive literature data mining. This is also intended to pave the way towards consistence incorporation of self-healing concepts into durability based design approaches for reinforced concrete structures, aimed at quantifying, with reliable confidence, the benefits in terms of slower degradation of the structural performance and extension of the service life-span. The main purpose of the study has been to quantify a “healable crack width” as a function of the structural service scenario as well as of the material composition variables, which could be used in serviceability limit state design calculations as well as quantify its influence on material durability parameters with the purpose of evaluating the kinetics of degradation mechanisms.  The final aim of the study is to propose, also through suitably built design charts, a straightforward input-output model to quickly predict.
   
   
6. Autonomous Evaluation of Fire-damaged Concrete Structures
   Speaker(s): M. Z. Naser
   We, as civil engineers, and practitioners, continue to favor traditional methods to assess the state of damaged structures in the aftermath of an extreme event (fire, earthquake etc.). Not only that these methods provide us with bare qualitative/opinion-based assessment, but also require the allocation of tremendous resources as well as physical presence of on-site experts – a condition that may not be possible in many scenarios (i.e. remote areas, toxicity/temperature, fear of imminent collapse etc.). The majority of these limitations can be overcome by leveraging recent technological advancements in parallel fields (i.e. computer science, robotics, sensing etc.). This article showcases how such technologies can be adopted to realize a modern, safe, instant, and realistic (quantitative) evaluation of damaged concrete structures. More specifically, this article explores concepts for autonomous assessment (AA) via computer vision (CV) and machine learning (ML) techniques and how AA can be used to; (1) identify failure mechanisms, and (2) propose suitable repair strategies.

Learning Objectives:
(1) Discuss the proper methods of leveraging AI for various applications (i.e. durability, fire resistance, chemical exposure etc.);
(2) Highlight case studies on successful AI applications in the area of concrete material and structural design (i.e. optimizing concrete mixture (e.g. UHPC, FRC), developing post-fire assessment methods etc.);
(3) Organize research and development efforts to modernize the concrete industry;
(4) Use AI as a new mean of analysis/assessment, together with traditional methods (i.e. testing, simulations, analytical derivations).

Other Featured Sessions:

• Legal Issues in Concrete Construction – Lessons Learned
• Adjusting Workability of Successful 3-D Concrete Printing
• Impact of Hot Weather Conditions on Concrete Repair
• Productivity in the Concrete Industry – Why Has it Stagnated and How Can ACI Help?

View all 45 sessions

Register Now »