Application of Artificial Intelligence and Machine Learning in Structural Engineering Design and Analysis Assignment Sample

• Type Assignment
• Downloads564
• Pages9
• Words2360

1. Introduction: AI & ML in Structural Engineering

Need in-depth insights on AI-driven structural engineering? Our Customized Assignment Help for College and University ensures high-quality research, tailored analysis, and expert guidance to boost your academic performance. From algorithmic reliability to data integration, we cover every crucial aspect of AI and ML in modern engineering practices.

1.1 Background

The integration of Artificial Intelligence (AI) and Machine Learning (ML) with underlying designing connotes a change in perspective from conventional observational techniques. Simulated intelligence and ML offer extraordinary potential to alter plan and investigation processes, promising improved exactness, effectiveness, and manageability. This extraordinary coordination tends to the constraints of manual estimations, opening roads for cutting-edge, information-driven arrangements in primary designing practices(Hooda et al., 2021).

1.2 Research problem

Considering the prospective advantages, there is a call to discover the challenges and opportunities which are connected with the execution of AI and ML in mechanical engineering. The main concerns included of the algorithmic reliability, data quality, besides the need for domain-specific replicas to discourse the multifaceted landscape of structural systems(Milne, 1989).

1.3 Research Aim and Objectives

The purpose of this topic is to measure the impact of AI and ML on structural engineering practices. Some of the major objectives comprises of the evaluation of the reliability of AI algorithms in structural study along with optimizing design processes by means of ML-driven insights, in addition talking about the challenges clogging widespread acceptance.

1.4 Main Themes for Literature Review

• Algorithmic Unwavering quality: Assessing the precision and strength of AI calculations in the underlying examination.
• Information Quality and Incorporation: Investigate strategies for guaranteeing top-notch information inputs and consistent coordination with artificial intelligence frameworks.
• Area Explicit Models: Explore the advancement of ML models customized to the complexities of underlying designing.
• Streamlining in Plan: Look at how artificial intelligence and ML add to enhancing the planning cycle, taking into account factors like expense, effectiveness, and supportability.

2. Main body

This section explores the integration of Artificial Intelligence (AI) and Machine Learning (ML) in structural engineering, focusing on theoretical foundations, data quality, design optimization, and existing research gaps. By critically analyzing relevant literature, this discussion highlights key concepts, methodologies, and challenges associated with AI-driven advancements in structural design and analysis.

2.1 Introduction

The incorporation of Artificial Intelligence (AI) and Machine Learning (ML) in structural engineering design and examination helps in characterizing development in a distinct way . In this area of study, it will bring in front the concepts, models, and theories. Through a thorough examination of a range of literature, this conversation aims to clarify important topics and concerns whilst critically evaluating important works. By analysing and differentiating across sources, the study will help in identifying some kind of information that lay the foundation for the study that is being suggested. A higher level of comprehension is provided by the combination of data across several theories, which also sheds light on the intricate relationship between machine learning and artificial intelligence in fundamental design.

2.2 Literature Review

Theoretical Foundations: Framing AI and ML Integration in Structural Engineering

Artificial Intelligence and ML compromise in hidden planning requires a strong speculative foundation to comprehend the psychological and computational cycles included. The Information Processing Theory remains an establishment in this endeavor, drawing in mental science to make sense of how PC-based knowledge and ML computations process information in the hidden assessment. This theory expresses that mental cycles drawn in with learning should be visible as information taking care of systems. Concerning essential planning, it lines up with the pith of how these estimations handle gigantic datasets, sorting out complex fundamental data and influencing the constancy and efficiency of the hidden examination process (Salehi and Burgueño, 2018). Digging further, the Sign Identification Hypothesis adds to how we could decipher algorithmic steadfastness, a fundamental point of view in reenacted knowledge-driven basic assessment. Laid out in brain research, this theory gives a sensible framework for knowing how computations separate between signal (definite basic encounters) and disturbance (missteps or mistakes). (Tapeh and Naser, 2022) can be translated according to this point of view, highlighting the meaning of making computations that recognize essential models amidst the complexity of data clatter. By applying the Sign Signal Detection Theory, the review gains insight into the nuanced challenges of algorithmic steadfastness in essential planning applications. Moving to the area of dynamics in fundamental planning, the Dual-Process Theory goes to the top. This hypothesis, proposed by (Málaga-Chuquitaype, 2022)), recommends that navigation includes two mental cycles: natural and intelligent reasoning. In the improvement of mixed models in primary designing, for example, those consolidating material science-based recreations with AI (Lu, Chen and Zheng, 2012), the Dual-Process Theory turns into an important hypothetical focal point. It assists us with grasping how these models balance natural example acknowledgment (AI) with intelligent, material science-based understanding, offering a nuanced way to deal with underlying examination. When taken as a whole, the recognised conceptual structures offer a solid basis for comprehending the mental aspects of AI and ML incorporation in the field of structural engineering. In addition to providing a framework for understanding the mechanisms that underlie algorithms, these hypotheses lay the groundwork for examination and more research into the complicated nature of computational dependability on making choices. These fundamental concepts become crucial in directing studies and their implementation as structural engineering endeavours depend more and more on AI and ML. They offer a prism by which the complexities of making decisions, analysing information, and building models may be understood, creating the foundation for future developments and breakthroughs in the discipline.

Scan QR code from mobile camera

Grab an Extra 10% OFF on WhatsApp order!

use discount

Data Quality and Integration: A DIKW Perspective

In the domain of underlying designing, the reconciliation of Artificial Intelligence (AI) and Machine Learning (ML) highlights the vital job of information. A hypothetical point of view that demonstrates instrumental in understanding the subtleties of information in this setting is the Information Data-Information-Knowledge-Wisdom (DIKW) model. This model gives a various levelled structure, depicting the dynamic change of crude information into significant bits of knowledge and noteworthy insight (Baskarada and Koronios, 2013). At the fundamental level, information, as crude and natural data, fills in as the structure block. The present literature, exemplified by concentrates, for example, those directed by (Intezari, Pauleen and Taskin, 2016), highlights the basic significance of excellent information in the progress of artificial intelligence and ML applications in primary designing. The DIKW model places that the nature of information is a forerunner to viable data age. These investigations dig into information preprocessing strategies, recognizing that the dependability of artificial intelligence models is dependent upon the nature of the data they are prepared on. As information advances along the pecking order, it changes into data through contextualization and organizing. (Riesener et al., 2019)dive into the joining difficulties, underlining the requirement for a consistent fuse of computer-based intelligence with existing primary designing work processes. The DIKW model assists with conceptualizing this change from crude information to organized data, featuring that the viability of information joining isn't just dependent on the nature of individual datasets but additionally on their strong fuse into a more extensive information system. Going ahead with the DIKW order, intellect developed from the trends and experiences obtained from data. Concentrates, for example, those by (Riesener et al., 2019)add to this information layer by exhibiting how successful information handling and joining lead to a more profound comprehension of primary frameworks. The DIKW model, in this specific circumstance, highlights that the information age is a powerful cycle formed by the quality and coordination of data obtained from different datasets. At the zenith of the DIKW order is shrewdness, addressing the use of information in a significant and logically suitable way. With regards to underlying designing, shrewdness might appear as the capacity to settle on informed choices in light of the experiences gathered from simulated intelligence and ML examinations. The DIKW model, while not unequivocally examined in the writing, offers a hypothetical focal point to conceptualize how the movement from information to shrewdness lines up with the overall objective of improving dynamics in primary designing through man-made intelligence and ML reconciliation (Rowley, 2007).

Overall, it can be said from the discussion that the DIKW model gives a significant hypothetical point of view to fathom the job of information in simulated intelligence and ML reconciliation inside underlying designing. From crude information to noteworthy insight, this model approaches the movement, accentuating the basic significance of information quality and compelling combination in the age of significant bits of knowledge and informed dynamics in the field of structural engineering.

Design Optimization: Guiding Improvement through Optimization Theory

In the scene of structural engineering, the quest for plan improvement is a focal topic, with Man-made reasoning assuming a groundbreaking part. Giving hypothetical support to this pursuit is the Optimization Theory, a numerical structure that directs the iterative course of improving a framework.

At its centre, the Optimization Theory offers an organized way to deal with deliberately further developing plans. Inside the literature, exemplified by studies directed by (Bandler, 1969), optimization is accomplished through the use of developmental calculations and support getting the hang of, lining up with the more extensive standards of advancement hypothesis. The substance of the Optimization Theory lies in the constant refinement of a framework to accomplish ideal results. (LI et al., 2021) dive into the use of developmental calculations for foundational layout enhancement. Developmental calculations, motivated by regular determination processes, iteratively refine and adjust answers to find the most productive plan in light of predefined goals. This lines up with the centre fundamentals of the Optimization Theory, where iterative refinement is vital to arriving at ideal states. Gupta et al. (2022) adds to the comprehension of plan improvement by applying support learning. Support learning, a subset of AI, includes preparing a framework to settle on choices by gaining connections with its current circumstance. With regards to primary designing, this includes streamlining underlying parts in light of criticism from the climate. The iterative idea of support learning reverberates with the standards of Optimization Theory, where steady variation prompts further developed framework execution. Besides, the Optimization Theory fits tending to multi-layered goals in underlying designing. It gives a numerical system to adjust contending plan rules, like underlying soundness, cost viability, and manageability. As AI and ML calculations improve plans, they explore complex, multi-faceted arrangement spaces, guaranteeing that the last plan meets the scope of predefined measures. The use of the Optimization Theory in underlying designing stretches out past the numerical domain to line up with more extensive designing objectives. It works with the investigation of plan options and the disclosure of inventive arrangements. The iterative idea of enhancement, as exhibited in the writing, resounds with the designing plan process, where consistent improvement and variation are fundamental.

2.3 Identifying Gaps

Regardless of progressions in the mix of Artificial Intelligence (AI) and Machine Learning (ML) in structural engineering, a basic assessment uncovers a prominent role in understanding the socio-specialized difficulties and hindrances obstructing boundless reception. To address this gap, the utilization of Artificial Intelligence (AI) and Machine Learning (ML) in structural engineering Technology Acceptance Model becomes crucial. TAM, proposed by Davis in 1989, gives a hypothetical focal point to unwind obstruction and acknowledgment designs inside client networks. By investigating apparent usability and thought to be beneficial, TAM offers experiences into the human elements impacting the reception of computer-based intelligence and ML advances in primary designing. This hypothetical methodology considers an extensive assessment of socio-specialized difficulties, enveloping client mentalities, hierarchical designs, and saw benefits(Mugo et al., 2017).

Conclusion

The overall literature review on the use of Artificial Intelligence (AI) and Machine Learning (ML) in structural engineering design and examination features a few central questions and basic focuses. Algorithmic unwavering quality arises as a focal worry, with research underlining the requirement for vigorous man-made intelligence calculations able to precisely explore the intricacies of underlying frameworks. Information quality and combination are critical, with an accentuation on preprocessing methods to guarantee top-notch inputs and consistent reconciliation with existing work processes. The improvement of domain-explicit models customized to the complexities of primary designing is a basic subject, exhibiting the significance of crossover moves toward joining physical science-based reproductions with AI strategies. The streamlining of the planning cycle through simulated intelligence and ML is an extraordinary perspective, with transformative calculations and support getting the hang of demonstrating power in accomplishing practical, effective, and maintainable plans. Concerning the socio-technical difficulties as well as impediments preventing the mainstream application of AI and ML in the field of structural engineering, a significant vacuum in research is noted. The suggested study intends to close this discrepancy by examining organisational and individual factors that affect the acceptance of technology through the use of the Technology Acceptance Model (TAM).

References

• Bandler, J.W., 1969. Optimization Methods for Computer-Aided Design. IEEE Transactions on Microwave Theory and Techniques, [online] 17(8), pp.533–552. https://doi.org/10.1109/tmtt.1969.1127005.
• Baskarada, S. and Koronios, A., 2013. Data, Information, Knowledge, Wisdom (DIKW): A Semiotic Theoretical and Empirical Exploration of the Hierarchy and its Quality Dimension. Australasian Journal of Information Systems, [online] 18(1). https://doi.org/10.3127/ajis.v18i1.748.
• Hooda, Y., Kuhar, P., Sharma, K. and Verma, N.K., 2021. Emerging Applications of Artificial Intelligence in Structural Engineering and Construction Industry. Journal of Physics: Conference Series, [online] 1950(1), p.012062. https://doi.org/10.1088/1742-6596/1950/1/012062.
• Intezari, A., Pauleen, D.J. and Taskin, N., 2016. The DIKW Hierarchy and Management Decision-Making. 2016 49th Hawaii International Conference on System Sciences (HICSS). [online] https://doi.org/10.1109/hicss.2016.520.
• LI, H., YANG, J., CHEN, G., LIU, X., ZHANG, Z., LI, G. and LIU, W., 2021. Towards intelligent design optimization: Progress and challenge of design optimization theories and technologies for plastic forming. Chinese Journal of Aeronautics, [online] 34(2), pp.104–123. https://doi.org/10.1016/j.cja.2020.09.002.
• Lu, P., Chen, S. and Zheng, Y., 2012. Artificial Intelligence in Civil Engineering. Mathematical Problems in Engineering, [online] 2012, pp.1–22. https://doi.org/10.1155/2012/145974.
• Málaga-Chuquitaype, C., 2022. Machine Learning in Structural Design: An Opinionated Review. Frontiers in Built Environment, [online] 8. https://doi.org/10.3389/fbuil.2022.815717.
• Milne, P.H., 1989. The application of artificial intelligence techniques to civil and structural engineering. Artificial Intelligence in Engineering, [online] 4(1), pp.54–55. https://doi.org/10.1016/0954-1810(89)90026-5.
• Mugo, D., Njagi, K., Chemwei, B. and Motanya, J., 2017. The Technology Acceptance Model (TAM) and its Application to the Utilization of Mobile Learning Technologies. British Journal of Mathematics & Computer Science, [online] 20(4), pp.1–8. https://doi.org/10.9734/bjmcs/2017/29015.
• Riesener, M., Dölle, C., Schuh, G. and Tönnes, C., 2019. Framework for defining information quality based on data attributes within the digital shadow using LDA. Procedia CIRP, [online] 83, pp.304–310. https://doi.org/10.1016/j.procir.2019.03.131.
• Rowley, J., 2007. The wisdom hierarchy: representations of the DIKW hierarchy. Journal of Information Science, [online] 33(2), pp.163–180. https://doi.org/10.1177/0165551506070706.
• Salehi, H. and Burgueño, R., 2018. Emerging artificial intelligence methods in structural engineering. Engineering Structures, [online] 171, pp.170–189. https://doi.org/10.1016/j.engstruct.2018.05.084.
• Tapeh, A.T.G. and Naser, M.Z., 2022. Artificial Intelligence, Machine Learning, and Deep Learning in Structural Engineering: A Scientometrics Review of Trends and Best Practices. Archives of Computational Methods in Engineering, [online] 30(1), pp.115–159. https://doi.org/10.1007/s11831-022-09793-w.