Dr. Soumyadip Das: Assistant Professor, Department of Civil Engineering at Dr. B. C. Roy Engineering College Durgapur, India
1. Article Details
Innovative approaches to concrete health monitoring: wavelet transform and artificial intelligence models was authored by Soumyadip Das, Aloke Kumar Datta, Pijush Topdar, and Apurba Pal and published in the Asian Journal of Civil Engineering. The article was published online on 23 September 2024 and appears in Volume 26, pages 107–120 (2025). The study focuses on structural health monitoring of concrete using Acoustic Emission (AE) sensing, Wavelet Transform (WT), and Artificial Intelligence (AI). Concrete slabs of different grades were experimentally prepared, and the Pencil Lead Break (PLB) technique was used to generate controlled AE signals. These signals were analyzed to identify the location of a simulated damage source. The study compares WT-based localization with an AI model and reports that the AI approach achieved lower calculation errors. The work is therefore positioned toward developing automated and potentially real-time monitoring techniques for concrete structures.
2. Novelty
The main novelty of the research is the integration of Acoustic Emission sensing with Artificial Intelligence for locating damage in concrete slabs. While AE and Wavelet Transform are established techniques, the study combines these methods with an AI-based prediction approach to reduce computational effort and localization error. The use of experimentally generated AE data from concrete slabs of different grades adds practical value to the investigation. Another notable aspect is the attempt to move from conventional signal-processing techniques toward automated damage localization. The study demonstrates that AI can potentially interpret AE information more efficiently than conventional WT-based calculations under the investigated experimental conditions. Thus, the novelty lies primarily in the integrated application and experimental validation of AE, WT, and AI for concrete health monitoring rather than in the invention of a completely new sensing technology.
3. Impact
The research has potential impact on structural health monitoring by providing a method for detecting and locating damage without interrupting the operation of a structure. The use of AE sensors allows structural information to be obtained from signals generated within concrete, while AI can automate the interpretation of large amounts of sensor data. If developed further, such a system could assist engineers in monitoring concrete slabs in bridges, buildings, industrial structures, dams, and other infrastructure. Early identification and localization of damage could help engineers concentrate inspection and maintenance activities on affected areas. The study also contributes to the broader development of intelligent infrastructure in which sensor data are continuously analyzed to support maintenance decisions. However, the reported impact is currently based on experimental laboratory-scale validation, so additional field-scale evidence is needed to establish performance under actual structural conditions.
4. Originality
The originality of the study comes from its experimental combination of AE monitoring, Wavelet Transform, and AI-based damage localization. Instead of using AI only as a theoretical prediction tool, the researchers generate their own AE data from concrete slabs and use those data for model development and validation. The comparison between WT and AI provides an additional original element because it evaluates whether AI can reduce the error associated with conventional signal-processing-based localization. The work also addresses the practical objective of real-time health monitoring rather than simply studying the characteristics of AE signals. Nevertheless, AE sensing, WT, and AI are individually well-established technologies; therefore, the originality should mainly be understood as their integrated application to concrete damage localization.
5. Experimental Rigor
The experimental methodology provides a controlled basis for evaluating the proposed technique. Concrete slabs of different grades were prepared, an AE monitoring system was deployed, and the PLB technique was used to generate repeatable acoustic-emission events. The resulting signals were processed using WT and AI-based methods, and the predicted damage location was subsequently validated using a simulated source. The use of controlled experiments makes it possible to compare the two approaches under similar conditions and reduces uncertainties associated with uncontrolled field environments. However, the experimental rigor could be strengthened through larger datasets, repeated experiments, actual crack formation under mechanical loading, independent testing datasets, different sensor configurations, environmental noise, and full-scale structural validation. Consequently, the research provides a useful experimental proof of concept, while broader validation remains necessary for field deployment.
6. Sustainability Impact
The proposed technology has an indirect but potentially important sustainability benefit because effective structural health monitoring can contribute to extending the service life of concrete infrastructure. If developing damage can be identified and localized at an early stage, maintenance can potentially be focused on affected areas rather than requiring extensive replacement. This may reduce the consumption of cement, aggregates, steel, and other construction materials and may also reduce demolition waste, construction energy consumption, and infrastructure downtime. Continuous monitoring can therefore support a maintenance strategy based on early intervention and service-life extension. However, the study does not appear to provide a quantitative life-cycle assessment or direct measurements of carbon-emission reductions. Therefore, the sustainability benefits should be considered potential outcomes of successful implementation rather than experimentally demonstrated environmental savings.
7. Applicability
The proposed approach is particularly applicable to slab-like concrete components because the experimental investigation was conducted using concrete slabs. Potential future applications include bridge decks, building slabs, industrial floors, parking structures, dams, tunnels, and other reinforced-concrete infrastructure. The technique could be incorporated into a monitoring system in which AE sensors continuously collect structural signals and an AI model automatically estimates the location of abnormal events. Its practical application would require consideration of sensor placement, signal attenuation, environmental noise, concrete variability, reinforcement arrangement, structural loading, sensor durability, data-processing requirements, and long-term model reliability. Therefore, the current study demonstrates applicability at the experimental level, while field implementation would require further validation under realistic structural and environmental conditions.
Research Portfolio
Soumyadip Das is an Assistant Professor in the Department of Civil Engineering at Dr. B. C. Roy Engineering College, Durgapur, with over a decade of academic and teaching experience. He completed his Ph.D. from the National Institute of Technology, Durgapur, in 2025, following his M.E. from IIEST Shibpur and B.Tech. from Birbhum Institute of Engineering & Technology. His academic and research interests broadly encompass structural health monitoring, acoustic emission techniques, artificial intelligence and machine learning applications, pavement engineering, and transportation engineering.
Online Profile
Soumyadip Das is a Civil Engineering academic and researcher associated with Dr. B. C. Roy Engineering College, Durgapur. His research work has been published in journals, conference proceedings, IEEE publications, Springer’s Lecture Notes in Civil Engineering, and Asian Journal of Civil Engineering. His scholarly contributions particularly focus on the application of acoustic emission, wavelet transformation, Shannon entropy, and machine learning techniques for damage and crack detection in reinforced concrete structures.
Education
Soumyadip Das received his Ph.D. from the National Institute of Technology, Durgapur, in 2025. He completed his Master of Engineering from the Indian Institute of Engineering Science and Technology, Shibpur (formerly BESU Shibpur), in 2015, and his Bachelor of Technology from Birbhum Institute of Engineering & Technology, Suri, in 2012. He completed his Higher Secondary education from Katwa Kashiram Das Institution, Katwa, in 2008 and Madhyamik from the same institution in 2006.
Research Focus
His research focuses primarily on structural health monitoring and damage assessment of reinforced concrete structures using acoustic emission techniques, wavelet transform, Shannon entropy, and artificial intelligence/machine learning models. His work also covers crack localization, concrete health monitoring, pavement performance and characterization, CBR improvement using solid waste, pedestrian movement characteristics, traffic behaviour, and transportation engineering. His recent research demonstrates the integration of experimental techniques with computational and data-driven approaches for structural damage identification.
Experience
Soumyadip Das began his academic career as a Lecturer at Basantika Institute of Engineering & Technology (Polytechnic), Ganpur, from August 2012 to August 2013. He subsequently served as an Assistant Professor at Birbhum Institute of Engineering & Technology, Suri, from August 2015 to March 2016, and at NSHM Knowledge Campus, Durgapur, from March 2016 to July 2017. Since July 2017, he has been serving as an Assistant Professor in the Department of Civil Engineering at Dr. B. C. Roy Engineering College, Durgapur.
Research Timeline & Activities
His research career has progressed from early work in pavement engineering and pedestrian traffic studies to advanced structural health monitoring and artificial intelligence-based damage detection. His publications between 2015 and 2020 addressed pedestrian flow, walking speeds, traffic behaviour, pavement performance, and geotechnical applications. From 2022 onward, his research increasingly focused on acoustic emission-based structural health monitoring, damage localization, wavelet analysis, Shannon entropy, and machine learning. His 2024–2025 publications further explored AI-assisted concrete health monitoring and crack localization in reinforced concrete slabs.
Awards & Honors
Soumyadip Das qualified the Graduate Aptitude Test in Engineering (GATE) in 2013 with a GATE score of 347. He is a professional member of the Institution of Engineers (India), the Indian Geotechnical Society (Kolkata Chapter), the Indian Society of Earthquake Technology, and the AI-ML Innovative Entrepreneurs and Engineers Association. He has also contributed to national and international academic conferences and research publications in civil and structural engineering.
Strengths for the Best Innovator Award
1. Innovative Integration of AI with Structural Health Monitoring
Dr. Soumyadip Das demonstrates strong innovation through the integration of Acoustic Emission (AE), Wavelet Transform, and Artificial Intelligence/Machine Learning for concrete health monitoring. His research moves beyond conventional inspection methods by developing data-driven approaches for damage detection and localization in reinforced concrete structures. The use of AI to interpret AE signals has the potential to reduce computational effort and improve the accuracy and automation of structural assessment. This combination of experimental sensing and intelligent data analysis represents a significant innovative contribution to civil engineering.
2. Strong Experimental-to-AI Research Approach
A major strength of his research is the connection between laboratory experimentation and computational intelligence. Concrete slabs of different grades were experimentally investigated using AE techniques, with the Pencil Lead Break method providing controlled acoustic-emission sources. The resulting experimental data were then used for Wavelet Transform and AI-based analysis. This approach demonstrates that his innovation is not limited to theoretical modelling; it is supported by physical experimentation and validation. Such integration strengthens the potential for translating research outcomes into practical engineering applications.
3. Advancement Toward Real-Time and Intelligent Infrastructure
Dr. Das’s research contributes to the development of intelligent and continuously monitored infrastructure. His work on damage localization aims to provide information about the presence and location of structural abnormalities without requiring interruption of structural operation. The integration of AI creates the possibility of automated interpretation of large volumes of sensor data and eventual real-time warning systems. This research direction is particularly relevant to bridges, buildings, concrete slabs, transportation infrastructure, and other large-scale civil engineering structures where continuous structural health information can improve maintenance planning and safety management.
4. Multidisciplinary and Evolving Research Portfolio
His research portfolio demonstrates innovation across several interconnected areas of civil engineering, including structural health monitoring, acoustic emission, signal processing, artificial intelligence, machine learning, pavement engineering, transportation engineering, and infrastructure assessment. His progression from conventional civil engineering investigations toward AI-assisted structural monitoring demonstrates an ability to incorporate emerging technologies into established engineering disciplines. The use of Wavelet Transform, Shannon entropy, machine learning, and experimental sensing indicates a multidisciplinary research approach that can generate new solutions to complex infrastructure-monitoring problems.
5. Potential for Sustainable and Industry-Relevant Innovation
The research has strong potential for practical and sustainable impact because intelligent damage monitoring can support early intervention, targeted maintenance, and extended service life of concrete infrastructure. Early localization of structural damage could reduce unnecessary repair or replacement, material consumption, construction waste, and associated resource use. His research therefore aligns technological innovation with the broader need for resilient and sustainable infrastructure. The combination of experimental validation, AI-based automation, and potential real-time deployment provides a strong foundation for developing innovative civil-engineering solutions with relevance to both academia and infrastructure practice.