A Bibliometric Analysis of the Applications of Artificial Intelligence Techniques to Engineering Design

Abdulhakeem Hassan Nurudeen; Abdullahi Yusuf Sada

doi:10.12688/f1000research.179509.1

Home Browse A Bibliometric Analysis of the Applications of Artificial Intelligence...

ALL Metrics

-

Views

-

Downloads

Get PDF

Get XML

Export

▬

✚

Review

A Bibliometric Analysis of the Applications of Artificial Intelligence Techniques to Engineering Design

[version 1; peer review: 1 not approved]

Abdulhakeem Hassan Nurudeen ¹, Abdullahi Yusuf Sada²

PUBLISHED 24 Apr 2026

Author details Author details

¹ Mechanical Engineering, University of Abuja Faculty of Engineering, Abuja, Federal Capital Territory, Nigeria
² Electrical and Computer Engineering, Baze University, Abuja, Federal Capital Territory, Nigeria

Abdulhakeem Hassan Nurudeen
Roles: Conceptualization, Data Curation, Formal Analysis, Investigation, Methodology, Project Administration, Supervision, Validation, Visualization, Writing – Original Draft Preparation, Writing – Review & Editing

Abdullahi Yusuf Sada
Roles: Data Curation, Formal Analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – Original Draft Preparation

OPEN PEER REVIEW

REVIEWER STATUS

This article is included in the Artificial Intelligence and Machine Learning gateway.

Abstract

In the era of technological sophistication, advancements and integration of artificial intelligence (AI) techniques in engineering design are revolutionizing numerous fields. Traditional processes are no longer effective in solving engineering problems. This study systematically examines scientific publications in the field of selected AI techniques in engineering design in various applications, such as deep learning, machine learning, and simulation. This mini-review also adopted a PRISMA framework-based methodology to extract data from the Scopus database and, then analyzed such data to identify research gaps and future directions in AI’s application to engineering design. A bibliometric analysis of AI in Engineering design was conducted to examine its role in engineering design, interdisciplinary collaboration, geographic distribution, and research focus. This study identifies critical research gaps and offers recommendations for future directions in AI applications for engineering design. The findings provide valuable insights into the state of the art and showcase valuable information for stakeholders to tune into the advances in AI techniques to enhance traditional engineering design processes.

Keywords

Artificial Intelligence, Engineering Design, Machine Learning, Simulation

Corresponding author: Abdulhakeem Hassan Nurudeen

Competing interests: No competing interests were disclosed.

Grant information: The author(s) declared that no grants were involved in supporting this work.

Copyright: © 2026 Nurudeen AH and Sada AY. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

How to cite: Nurudeen AH and Sada AY. A Bibliometric Analysis of the Applications of Artificial Intelligence Techniques to Engineering Design [version 1; peer review: 1 not approved]. F1000Research 2026, 15:619 (https://doi.org/10.12688/f1000research.179509.1) First published: 24 Apr 2026, 15:619 (https://doi.org/10.12688/f1000research.179509.1) Latest published: 24 Apr 2026, 15:619 (https://doi.org/10.12688/f1000research.179509.1)

1. Introduction

Traditional approaches to Engineering Design (ED) processes are based on intuition involving scientific, experimental, creative methods, and expert knowledge of the process. For instance, traditional process planning is executed primarily based on experience in creating products using machine tools.^1,2

Recent advancements and the rapid adoption of artificial intelligence approaches have simplified and revolutionized engineering design.³ Artificial Intelligence (AI) is known as “using computer algorithms to imitate biotic mental processes or activities”⁴ to execute tasks such as learning about processes, understanding, estimating, problem-solving and decision-making in several areas of engineering applications that cut across all disciplines.

The adoption of this novel methodology transforms how processes are designed and executed in the shortest possible time, with the least cost, precise solutions and further completion rates than generic human approaches.⁵

The desire for better solutions to challenging world problems has led engineers to push for optimal solutions using modern technologies to conceptualize, evaluate, and compare many candidate solutions without the need for physical prototypes,⁶ using computational tools and Computer-Aided Design (CAD) systems.⁷ These systems have evolved significantly with their sophisticated modelling, simulation and analysis capabilities.⁸ AI has further transformed these systems by introducing automation, decision-making support and advanced analytic support through Machine Learning (ML), Neural Networks (NN), and Generic Algorithms (GA), which are now integrated into CAD systems, making it possible to explore and execute complex and data-driven tasks.^9,10

This study provides a comprehensive review of the development and applications of AI in Engineering Design over three broad clusters of application: AI technologies in the ED, Engineering Design Methodologies and their practical applications across engineering.

To highlight the impact of AI, this study reviewed several studies using AI techniques approximately 1653 studies were found between 1970–2025, a filter was used to narrow the review to between 2010–2025 which reduced the number to 142, on subject areas limited to engineering, energy and chemical engineering showed 763 results from articles, conference papers, reviews, conference reviews etc, and the keyword search showed 5962 with a minimum of five occurrences resulting in over 316 keywords:- engineering design, artificial intelligence, deep learning, machine learning, product design, design, optimization, decision support systems etc., as shown in Figure 1.

Figure 1. Presents the keyword search by occurrence.

In Figure 1, the magnified red circumference denotes the dominance of the 'engineering design' search index, substantively outperforming concurrent keywords such as computer-aided design and machine learning frameworks.

2. Methodology

2.1 Bibliometric analysis

An in-depth bibliometric examination was conducted, focusing on AI within the engineering design framework. The current research and development landscape in AI and Engineering Design has been analyzed through a wide range of articles and reviews. This approach allows researchers to examine trends, interconnections and trends among scholarly publications, providing a deeper exploration of research themes and collaborative networks within the field. Through analysis of citation patterns, co-authorship relations and keyword frequencies, among others.

In this study, co-citation, co-authorship, and co-author maps are used as methods to highlight the relationships between studies, authors and topics. The VOS viewer software was utilized to automatically generate occurrences and co-occurrence matrices, clustering of related research and similarity measures, offering a detailed map of how AI is integrated into engineering design.¹¹

2.2 Literature retrieval

This step involved the identification of relevant search terms and keywords to search for relevant literature related to the chosen subject area. The selection of relevant publications within AI and Engineering design from the Scopus database is due to its distinction in comprehensive coverage of wide academic articles and publications with high quality, accessibility and global reach among other features. This search was achieved through set of keywords “Artificial Intelligence”, “Machine Learning” and “Engineering Design” with a focus on title, abstract and keyword search, resulting in the compilation of 1653 papers between 1976–2025.

A search filter was applied, which reduced the number of papers compiled to 1142 and publication year from to 2010–2025.

Table 1 presents the breakdown of the top searches, average publication year, citations and occurrence of keywords.

Table 1. Breakdown of the top 30 searches.

Table 1 presents the breakdown of the top searches, average publication year, citations and occurrence of keywords. The Table was extracted from the VOS Viewer software. It shows the keyword search and the research output in the field.

Label	Links	Total Link Strength	Occurrences	Avg. Pub. Year	Avg. Citations	Avg. Norm. Citations
Engineering Design	112	998	226	2021	17.6239	0.9175
Artificial Intelligence	107	975	220	2020	46.2818	1.1718
Machine Learning	104	869	184	2022	22.9076	1.1599
Machine-Learning	98	670	129	2023	9.2636	0.9828
Engineering Education	80	432	81	2021	17.3704	0.612
Design	91	359	77	2018	17.7792	0.9384
Learning Systems	98	422	76	2021	30.75	0.9603
Product Design	75	313	62	2020	14.9032	1.2555
Optimization	73	276	53	2020	108.8491	1.6613
Students	52	296	52	2020	9.2308	0.4247
Deep Learning	78	244	48	2022	36.4792	0.9726
Computer Aided Design	77	318	46	2021	25.3913	0.8925
Learning Algorithms	82	268	44	2021	14.6364	0.9708
Machine Design	78	237	39	2023	9.4103	0.8795
Forecasting	51	182	38	2022	26.5263	1.4376
Neural Networks	70	224	38	2021	41.1842	1.4366
Curricula	45	215	37	2020	8.2973	0.398
Decision Making	79	194	37	2020	54.8919	1.1479
Optimisations	61	183	31	2022	67.7742	1.1182
Teaching	42	177	29	2019	15.5517	0.555
Engineering Design Process	54	143	28	2018	20.1429	1.0021
Performance	50	124	28	2023	78.3929	1.3744
Benchmarking	52	152	27	2022	192.2963	2.5121
Iterative Methods	61	145	25	2021	12.76	0.8013
Data Driven	58	133	24	2023	10.9583	1.0108
Genetic Algorithms	59	139	24	2020	23.7083	1.0071
Data-Driven Design	61	182	23	2023	22.4348	1.3811
Optimization Algorithms	38	123	23	2022	150.7826	2.1106
Computer-Aided Design	53	162	22	2022	14.4091	0.8236
Decision Support Systems	39	97	22	2017	18.5455	1.0247

Figure 2 shows the research output on engineering design and AI by country, showing that the United States is the leading country, followed by China and the United Kingdom in research output based on engineering design-induced AI.

Figure 2. Bibliometric distribution of research output by country.

The analysis identifies the United States (represented by the pink node) and China (represented by the blue node) as the leading contributors to the global literature on engineering design and AI frameworks.

From Table 2, there are over 200 documents from the United States with China having 141 output per annum and the United Kingdom as the third largest in research projects on AI-based Engineering Design.

Table 2. Top 20 countries by research output on engineering design and AI. Table 2 presents the top 20 countries that engage in research related to engineering design and artificial intelligence techniques.

Country	Documents	Citations	Total Link Strength
United States	227	1	7633
China	141	16	9731
United Kingdom	45	450	2680
India	34	213	4853
Canada	32	3	2144
Australia	31	33	3132
Germany	22	209	331
Singapore	18	7	2158
Italy	16	1749	876
Malaysia	16	1	1573
Turkey	16	564	1253
Iran	15	942	2714
Saudi Arabia	15	17	3841
Hong Kong	14	0	1232
South Korea	14	8	2357
Taiwan	14	4227	1861
Spain	13	1210	1123
Netherlands	11	0	495
France	10	15	449
Japan	10	52	639

Figure 3 and Table 3. the study identifies key disciplinary specializations and institutional adopters of AI-based engineering design. The visualization confirms the MIT Department of Mechanical Engineering as the preeminent institution in this field. Supporting data in Table 3 shows the scholarly impact through metrics such as document frequency, citation impact, and inter-institutional link strengths.

Figure 3. Institutional distribution of global research output.

The visualization highlights the departmental origins of the research data, where the MIT Department of Mechanical Engineering is identified as a dominant cluster. The magnitude of its index reflects the institution's significant volume of scholarly contributions to the analyzed domain.

Table 3. Bibliometric performance summary: Comparative analysis of publication output, citation impact, and relational link strength.

Table 3 shows the institutional distribution of research papers, highlighting the specific thematic focus of various organizations on the application of AI methodologies within the engineering design domain.

Organization	Documents	Citations	Total Link Strength
Department Of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, 02139, Ma, United States	8	236	914
Department Of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, 15213, Pa, United States	5	55	587
Massachusetts Institute of Technology, Cambridge, Ma, United States	5	12	273
Department Of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pa, United States	4	30	1148
Department Of Mechanical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, 02139, Ma, United States	3	27	325
Department Of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Ma, United States	3	47	343
School Of Civil Engineering, Shenyang Jianzhu University, Shenyang, China	3	22	598
School Of Civil Engineering, Southeast University, Nanjing, China	3	12	504
Singapore University of Technology And Design, Singapore	3	35	359
The University of New South Wales, Kensington, 2052, Nsw, Australia	3	51	177
Applied Science Research Center, Applied Science Private University, Amman, 11931, Jordan	2	22	1926
C-Core, 1 Morrissey Rd, St. John’s, A1b 3x5, Nl, Canada	2	191	256
Centre For Artificial Intelligence Research and Optimisation, Torrens University Australia, Australia	2	2999	1088
Colegio De Ciencias E Ingeniería, Universidad San Francisco De Quito, Quito, Ecuador	2	5	684
College Of Civil Engineering and Architecture, Zhejiang University, Hangzhou, China	2	10	436
College Of Computer Science and Artificial Intelligence, Wenzhou University, Zhejiang, Wenzhou, 325035, China	2	46	1681
College Of Computer Science and Technology, Changchun Normal University, Jilin, Changchun, 130032, China	2	46	1681
Data-Driven Innovation Lab, Singapore University of Technology and Design, 8 Somapah Road, Singapore, 487372, Singapore	2	17	523
Department Of Aerospace and Ocean Engineering, Virginia Tech, Blacksburg, 24060, Va, United States	2	99	100
Department Of Civil Engineering, Istanbul University-Cerrahpaşa, Istanbul, 34320, Turkey	2	28	411

3. Overview on AI technologies in engineering design

3.1 Machine Learning (ML)

Machine learning is one of the most prominent AI technologies used in ED, and it helps with the optimization of designs and analysis of large datasets and patterns through a systematic framework to manage all engineering design activities, thereby increasing operations efficiency.¹² “Engineering design is a broad field encompassing domains of Government, Industry, technology, education, social science and practical use”.¹³ The current capabilities of AI with large language models (LLM) such as Generative Pre-trained Transform Models (GPT) have demonstrated ways of sharing knowledge through conversations. For example, OpenAI’s ChatGPT, which explores a vast repository of information and interactive response format, is now enhancing traditional design processes.^5,14–16

3.2 Deep learning

This branch of AI mimics the human brain and enhances its ability to handle complex design tasks through in-depth data training.¹⁷ It also plays a crucial role in generating design solutions, predictions and performance analysis, which are achieved through computer vision from images and videos, text, and sound, which enables designers to identify and solve problems with high efficiency and quality.¹⁸

Deep learning algorithms process and analyze a large amount of data using the neural network structure of the human brain with high accuracy and efficiency.^19,20 These features enable deep learning to be robust in navigating through large datasets, offering a transformative advantage to designers and engineers to improve designs through a pre-emptive approach in the design process.¹³

In manufacturing processes, deep learning is essential for identifying usability issues or designing defects in manufactured products. Deep learning uses historical data on similar products, customer feedback, claims and production ledgers to identify products that are likely to cause customer dissatisfaction or increase production costs.²¹

Deep learning also offers an innovative and dynamic approach to design by analyzing datasets to produce novel designs that may not be obvious, thus inspiring designers to adopt new concepts and solutions.^13,22

The integration of AI-driven techniques into the design process has paved the way for a collaborative and iterative approach to development where all stakeholders exploit the deep learning methodology to make data-driven decisions that optimize performance, user experience, and ease of manufacturing.

Moreover, as these technologies evolve, their impact in engineering design will eventually grow, guiding the development of more intelligent, reactive and robust designs.¹⁵ The evolution of AI into design has provided powerful tools for analyzing data, identifying hitches and providing innovative solutions to solve challenging problems.

3.3 Simulation

AI-driven simulation techniques are shaping the way engineering design is performed, from manufacturing processes to product design and systems that are transforming the world. These tools have become the latest norm as they provide dynamic solutions to fluid dynamics through computational fluid dynamics (CFD), finite element analysis (FEA) and manufacturing process simulation.²⁰ The CFD technology can simulate the flow of gases and liquids in the design, and FEA predict the reactions of materials under forces, while manufacturing process simulators showcase the manufacturing processes, supply chain and other process models. Simulation forecasts the behaviors of systems and optimizes parameters to look for desired outcomes before embarking on real plant production and design to save costs, time, and resources.^11,23,24

4. Specific AI applications to engineering design

To showcase the application domains of AI techniques to ED, the following section provides several situations backed by the research conducted:

Mechanical Engineering: One of the main areas that has revolutionised traditional design is Computer-Aided Design (CAD) systems. Since its introduction in the sixties (1960) the use of computer technology has helped designers to enhance their work.²⁵ From traditional two-dimensional drawing tools to complex three-dimensional modelling, simulation and optimization systems.²⁶ CAD technology has become essential in various fields such as engineering, mechanical design, automotive, and industrial design.²⁷

AI has transformed CAD systems with tools for automation, decision-making support and advanced analytical capabilities through machine learning, neural networks and generic algorithms, which are integrated into CAD software to handle complex and data-driven tasks.²⁸

AI technology has improved CAD systems and predicted possible problems during design and proffer solutions, which subsequently reduces the uncertainties in the design processes, and increases reliability and efficiency.^27,29 AI algorithms have also boosted the capabilities of CAD systems to generate generative design, offering multiple design solutions that suits different situations. Through this approach, numerous design possibilities, optimizations of functionalities and visual appeals have become achievable.^7,30

Another challenging task is the design of mechanical mechanisms subjected to complex physical constraints.²⁶ Understanding the relationship between motion and mechanism design is essential because of the non-linear characteristics between the mechanism classes and boundary conditions.²⁶ When solved analytically, an in-depth knowledge of the mechanism is required. AI has helped designers to optimize these designs through simulations and data-driven methods to train data that will provide new designs with little calculation.³¹ Several AI techniques, such as conditional adversarial networks, natural-language models and autoencoder networks are used for the synthesis of mechanisms, creation of multibody simulation codes or models for rapid prototyping, and representation of target paths in a compressed lower-dimensional feature space.^28,31–37

5. Conclusions and future directions

The evolution of AI and its applications is finding ground in various fields, and is not limited to engineering design. In engineering design, AI is utilized for several purposes, such as CAD systems to automate tasks based on predefined rules, integrating advanced techniques that integrate graphical, verbal and gestural inputs into refined design concepts, predictive analytics and real-time monitoring to enhance systems.

Data transformation is also an area that is critical in engineering design, because of its scarcity, high cost of acquisition and limited access during operations. AI techniques help in developing minimal datasets that can address such issues showcasing significant variations in system responses with small parameter changes making simulations practical, and to setting benchmarks to predict system performance and requirements of data-driven models.

The integration of AI techniques also enhances design optimization, as it offers sophisticated tools to aid in rapid design concepts and reduced lead times to produce new products in the market. These techniques have demonstrated their versatility in all aspects of business, manufacturing, design and life, particularly in engineering design where AI is transforming computer software to make data-driven decisions, and simulate intelligent behaviors to enhance efficiency and product quality.

In conclusion, the rapid evolution of digital ecosystem AI in engineering design has the potential to drive the engineering industry and provide systematic and dynamic capabilities to transform traditional engineering design processes into enhanced capabilities.

Data availability

AI Techniques in “Engineering Design Review Data”, Mendeley Data, V1, doi: 10.17632/849fxw2s8d.1.³⁸

Data are available under the terms of the Creative Commons Attribution 4.0 International license (CC-BY 4.0).

References

1. Khaleel M, Ahmed A, Alsharif AH: Artificial Intelligence in Engineering. Brilliance: Research of Artificial Intelligence. 2023; 3: 32–42. Publisher Full Text Reference Source
2. Yüksel N, Börklü HR, Sezer HK, et al.: Review of artificial intelligence applications in engineering design perspective. Eng. Appl. Artif. Intell. 2023; 118: 105697. Publisher Full Text
3. Khanolkar P, Vrolijk A, Olechowski A: Mapping artificial intelligence-based methods to engineering design stages: a focused literature review. Artificial Intelligence for Engineering Design, Analysis and Manufacturing. 2023; 37. Reference Source
4. Alhakeem MRH, Ilham DN: Application of Artificial Intelligence in Mechanical Engineering. Brilliance: Research of Artificial Intelligence. 2022. Reference Source
5. Zhang F: Design and Implementation of Industrial Design and Transformation System Based on Artificial Intelligence Technology. Math. Probl. Eng. 2022; 2022: 1–9. Publisher Full Text Reference Source
6. Zou Q, Wu Y, Liu Z, et al.: Intelligent CAD 2.0. ArXiv. 2024; abs/2410.03759. Reference Source
7. Obaid AJ, Sharma S: Recent Trends and Development of Heuristic Artificial Intelligence Approach in Mechanical System and Engineering Product Design. Saudi J Eng Technol. 2020; 05: 86–93. Publisher Full Text Reference Source
8. Rossi L, Winands M, Butenweg C: Monte Carlo Tree Search as an intelligent search tool in structural design problems. Eng. Comput. 2021; 38: 3219–3236. Publisher Full Text Reference Source
9. Sidorenko DO, Gavaza KG, Starodubcev NO, et al.: Generative Design of Physical Objects using Modular Framework. Eng. Appl. Artif. Intell. 2022; 119: 105715. Reference Source
10. Singh MM, Chen X, Geyer P: Explainable AI for engineering design: A unified approach of systems engineering and component-based deep learning. Adv. Eng. Inform. 2021; 62: 102843. Reference Source
11. Alghazo M, Ahmed V, Bahroun Z: Exploring the applications of artificial intelligence in mechanical engineering education. Frontiers in Education. Frontiers Media SA; 2025; p. 1492308.
12. Málaga-Chuquitaype C: Machine Learning in Structural Design: An Opinionated Review. Front Built Environ. 2022. Reference Source
13. Elrefaie M, Qian J, Wu R, et al.: AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design. ArXiv. 2025; abs/2503.23315. Reference Source
14. Fallacara G, Fanti MP, Parisi F, et al.: AI-driven image generation for enhancing design in digital fabrication: urban furnishings in historic city centres. VIPERC. 2023. Reference Source
15. Mondal S, Goswami S: Rise of Intelligent Machines: Influence of Artificial Intelligence on Mechanical Engineering Innovation. Spectrum of Engineering and Management Sciences. 2024; 2: 46–55. Publisher Full Text Reference Source
16. Zou N, Wang Q, Li X: Practical Exploration of Simulation Technology Based on Artificial Intelligence in Engineering Design. Scientific Journal of Technology. 2024; 2: 46–55. Publisher Full Text Reference Source
17. El Naqa I, Murphy MJ: What Are Machine and Deep Learning?. Machine and Deep Learning in Oncology, Medical Physics and Radiology. Cham: Springer International Publishing; 2022; pp. 3–15. Publisher Full Text
18. Brisco R, Hay L, Dhami S: EXPLORING THE ROLE OF TEXT-TO-IMAGE AI IN CONCEPT GENERATION. Proceedings of the Design Society. 2023; 3: 1835–1844. Publisher Full Text Reference Source
19. Kamolov S: Machine learning methods in civil engineering: a systematic review. Annals of Mathematics and Computer Science. 2024; 21: 181–191. Publisher Full Text Reference Source
20. Payrebrune K, et al.: The impact of AI on engineering design procedures for dynamical systems. ArXiv. 2024; abs/2412.12230. Reference Source
21. Yang J, Liao J, Feng L: Artificial intelligence inspired freeform optics design: a review. ArXiv. 2024; abs/2410.03554. Reference Source
22. Rudolph S: On Some Artificial Intelligence Methods in the V-Model of Model-Based Systems Engineering. International Conference on Model-Driven Engineering and Software Development. 2024. Reference Source
23. Tolk A, Barry P, Doskey SC: Using modeling and simulation and artificial intelligence to improve complex adaptive systems engineering. International Journal of Modeling, Simulation, and Scientific Computing. 2022; 13(02): 2241004. Publisher Full Text
24. Shen Y, Yu P, Lu H, et al.: An AI-based virtual simulation experimental teaching system in space engineering education. Comput. Appl. Eng. Educ. 2021; 29(2): 329–338. Publisher Full Text
25. Zou Q, Wu Y, Liu Z, et al.: Intelligent CAD 2.0. Visual Informatics. 2024; 8: 1–12. Publisher Full Text
26. de Payrebrune KM , et al.: The impact of AI on engineering design procedures for dynamical systems. arXiv preprint arXiv:2412.12230. 2024.
27. Saini M: AI and its Application in CAD. Int J Adv Eng Manag. 2023; 5(4): 1874–1879.
28. Hunde BR, Woldeyohannes AD: Future prospects of computer-aided design (CAD)–A review from the perspective of artificial intelligence (AI), extended reality, and 3D printing. Results Eng. 2022; 14: 100478. Publisher Full Text
29. Balagopal PA: Impact of Artificial Intelligence on Mechanical Engineering: A Comprehensive Overview. Int J Innov Sci Res Technol. 2024; 9(7): 1829–1832.
30. Yoo S, Lee S, Kim S, et al.: Integrating deep learning into CAD/CAE system: generative design and evaluation of 3D conceptual wheel. Struct. Multidiscip. Optim. 2020; 64: 2725–2747. Reference Source
31. Chen C-H: Application of Multiple Deep Neural Networks to Multi-Solution Synthesis of Linkage Mechanisms. Machines. 2023; 11(11): 1018. Publisher Full Text
32. Yim NH, Ryu J, Kim YY: Big data approach for synthesizing a spatial linkage mechanism. 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2023; pp. 7433–7439.
33. Röder B, Ebel H, Eberhard P: Towards intelligent design assistants for planar multibody mechanisms. PAMM. 2023; 23(4): e202300060. Publisher Full Text
34. Lee S, Kim J, Kang N: Deep Generative Model-based Synthesis of Four-bar Linkage Mechanisms with Target Conditions. arXiv preprint arXiv:2402.14882. 2024.
35. Gerstmayr J, Manzl P, Pieber M: Multibody models generated from natural language. Multibody Syst. Dyn. 2024; 62(2): 249–271. Publisher Full Text
36. Nurizada A, Purwar A: Transforming Hand-Drawn Sketches of Linkage Mechanisms Into Their Digital Representation. J. Comput. Inf. Sci. Eng. 2024; 24(1). Publisher Full Text
37. Deshpande S, Purwar A: A machine learning approach to kinematic synthesis of defect-free planar four-bar linkages. J. Comput. Inf. Sci. Eng. 2019; 19(2): 021004. Publisher Full Text
38. Hassan NA, Sada AY: AI Techniques in Engineering Design Review Data. Mendeley Data. 2026; V1. Publisher Full Text

Comments on this article Comments (0)

Version 1

VERSION 1 PUBLISHED 24 Apr 2026

Author details Author details

¹ Mechanical Engineering, University of Abuja Faculty of Engineering, Abuja, Federal Capital Territory, Nigeria
² Electrical and Computer Engineering, Baze University, Abuja, Federal Capital Territory, Nigeria

Abdulhakeem Hassan Nurudeen
Roles: Conceptualization, Data Curation, Formal Analysis, Investigation, Methodology, Project Administration, Supervision, Validation, Visualization, Writing – Original Draft Preparation, Writing – Review & Editing

Abdullahi Yusuf Sada
Roles: Data Curation, Formal Analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – Original Draft Preparation

Competing interests

No competing interests were disclosed.

Grant information

The author(s) declared that no grants were involved in supporting this work.

Article Versions (1)

version 1

Published: 24 Apr 2026, 15:619

https://doi.org/10.12688/f1000research.179509.1

Copyright

© 2026 Nurudeen AH and Sada AY. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download

Export To

metrics

	Views	Downloads
F1000Research	-	-
PubMed Central Data from PMC are received and updated monthly.	-	-

Citations

0

SEE MORE DETAILS

CITE

how to cite this article

Nurudeen AH and Sada AY. A Bibliometric Analysis of the Applications of Artificial Intelligence Techniques to Engineering Design [version 1; peer review: 1 not approved]. F1000Research 2026, 15:619 (https://doi.org/10.12688/f1000research.179509.1)

NOTE: If applicable, it is important to ensure the information in square brackets after the title is included in all citations of this article.

track

receive updates on this article

Track an article to receive email alerts on any updates to this article.

Open Peer Review

Version 1

VERSION 1

PUBLISHED 24 Apr 2026

Views

8

Reviewer Report 12 May 2026

Sina Sarfarazi, University of Naples “Federico II”, Naples, Italy

Not Approved

https://doi.org/10.5256/f1000research.198030.r482991

Comments

1. The review methodology is not sufficiently consistent. The abstract states that a PRISMA-based methodology was used, but the manuscript does not show a proper PRISMA flow diagram or a traceable screening process. The ... Continue reading

Comments

1. The review methodology is not sufficiently consistent. The abstract states that a PRISMA-based methodology was used, but the manuscript does not show a proper PRISMA flow diagram or a traceable screening process. The reported numbers are also confusing: the text mentions 1653 papers from 1970–2025, then filtering to 2010–2025, then 142 papers, 763 results by subject area, and 5962 keyword search results. Later, the methodology says the filter reduced the dataset to 1142 papers. These numbers must be reconciled. Without a clear record-selection process, the bibliometric results cannot be verified.

2. The bibliometric analysis is too shallow. VOSviewer is used to generate keyword, country, and institutional maps, but the interpretation is limited. For example, Table 1 lists keyword occurrences and citations, but the paper does not explain what the clusters mean for engineering design research. It should interpret why “engineering design,” “artificial intelligence,” “machine learning,” “optimization,” “benchmarking,” and “data-driven design” form certain clusters and how these clusters connect to design tasks. The current analysis mostly reports what is visible in the figures and tables.

3. There are serious issues in the country and institutional data. Table 2 reports the United States with 227 documents but only 1 citation, while China has 141 documents and 16 citations. These values are not credible for a Scopus-based bibliometric dataset unless the citation column is mislabeled or incorrectly extracted. The text also states that China has “141 output per annum,” which is not what the table shows. Table 3 contains duplicate institutional entries for MIT and Carnegie Mellon under slightly different names. The authors need to clean affiliation data and verify all bibliometric fields before drawing conclusions.

4. The figures are not fitting in criteria of journal standard quality for a bibliometric paper. The VOSviewer maps are crowded and difficult to read, especially the keyword and institutional maps. The figures also need clearer legends, cluster labels, minimum occurrence thresholds, and interpretation of node size and link strength. At present, the figures look like raw software outputs rather than carefully prepared scientific evidence.

5. The technical discussion of AI methods is too basic. Sections on machine learning, deep learning, and simulation mostly provide generic descriptions. They do not critically discuss engineering design tasks such as topology optimization, generative design, inverse design, CAD/CAE automation, design-space exploration, surrogate modeling, uncertainty-aware design, or human-AI co-design. This is a major weakness because the paper is supposed to review AI in engineering design, not AI in general.

6. The specific application section is underdeveloped. The manuscript briefly discusses CAD, generative design, and mechanism synthesis, but it does not provide a structured comparison across engineering fields. Mechanical, civil, aerospace, manufacturing, and product design should not be mixed without a framework. The authors should classify applications by design stage, AI method, data source, validation approach, and engineering output. This would make the paper useful to readers instead of only giving a broad overview.

7. The conclusions are too general and are not strongly supported by the bibliometric analysis. Statements such as AI transforming engineering design, reducing lead time, and improving product quality may be true, but the paper does not quantify these claims using the reviewed corpus. The conclusion should instead report evidence-based findings from the dataset: dominant keywords, growth trends, leading countries/institutions, method clusters, and underdeveloped research directions.

Is the topic of the review discussed comprehensively in the context of the current literature?

No
Are all factual statements correct and adequately supported by citations?

No
Is the review written in accessible language?

Partly
Are the conclusions drawn appropriate in the context of the current research literature?

No

Competing Interests: No competing interests were disclosed.

Reviewer Expertise: Intersection of computational mechanics and applied AI, finite element modelling (Abaqus), structural verification, and developing Python-based automation for simulations, post-processing, and reporting.

I confirm that I have read this submission and believe that I have an appropriate level of expertise to state that I do not consider it to be of an acceptable scientific standard, for reasons outlined above.

CITE

Report a concern

Respond or Comment

Comments on this article Comments (0)

Version 1

VERSION 1 PUBLISHED 24 Apr 2026

Open Peer Review

Reviewer Status

Reviewer Reports

	Invited Reviewers
	1
Version 1 24 Apr 26	read

Sina Sarfarazi, University of Naples “Federico II”, Naples, Italy

Comments on this article

All Comments(0)

Add a comment

Sign up for content alerts

Browse by related subjects

Back to all reports

Reviewer Report

8 Views

12 May 2026 | for Version 1

Sina Sarfarazi, University of Naples “Federico II”, Naples, Italy

8 Views Cite this report Responses(0)

Not Approved

Comments

1. The review methodology is not sufficiently consistent. The abstract states that a PRISMA-based methodology was used, but the manuscript does not show a proper PRISMA flow diagram or a traceable screening process. The reported numbers are also confusing: the text mentions 1653 papers from 1970–2025, then filtering to 2010–2025, then 142 papers, 763 results by subject area, and 5962 keyword search results. Later, the methodology says the filter reduced the dataset to 1142 papers. These numbers must be reconciled. Without a clear record-selection process, the bibliometric results cannot be verified.

2. The bibliometric analysis is too shallow. VOSviewer is used to generate keyword, country, and institutional maps, but the interpretation is limited. For example, Table 1 lists keyword occurrences and citations, but the paper does not explain what the clusters mean for engineering design research. It should interpret why “engineering design,” “artificial intelligence,” “machine learning,” “optimization,” “benchmarking,” and “data-driven design” form certain clusters and how these clusters connect to design tasks. The current analysis mostly reports what is visible in the figures and tables.

3. There are serious issues in the country and institutional data. Table 2 reports the United States with 227 documents but only 1 citation, while China has 141 documents and 16 citations. These values are not credible for a Scopus-based bibliometric dataset unless the citation column is mislabeled or incorrectly extracted. The text also states that China has “141 output per annum,” which is not what the table shows. Table 3 contains duplicate institutional entries for MIT and Carnegie Mellon under slightly different names. The authors need to clean affiliation data and verify all bibliometric fields before drawing conclusions.

4. The figures are not fitting in criteria of journal standard quality for a bibliometric paper. The VOSviewer maps are crowded and difficult to read, especially the keyword and institutional maps. The figures also need clearer legends, cluster labels, minimum occurrence thresholds, and interpretation of node size and link strength. At present, the figures look like raw software outputs rather than carefully prepared scientific evidence.

5. The technical discussion of AI methods is too basic. Sections on machine learning, deep learning, and simulation mostly provide generic descriptions. They do not critically discuss engineering design tasks such as topology optimization, generative design, inverse design, CAD/CAE automation, design-space exploration, surrogate modeling, uncertainty-aware design, or human-AI co-design. This is a major weakness because the paper is supposed to review AI in engineering design, not AI in general.

6. The specific application section is underdeveloped. The manuscript briefly discusses CAD, generative design, and mechanism synthesis, but it does not provide a structured comparison across engineering fields. Mechanical, civil, aerospace, manufacturing, and product design should not be mixed without a framework. The authors should classify applications by design stage, AI method, data source, validation approach, and engineering output. This would make the paper useful to readers instead of only giving a broad overview.

7. The conclusions are too general and are not strongly supported by the bibliometric analysis. Statements such as AI transforming engineering design, reducing lead time, and improving product quality may be true, but the paper does not quantify these claims using the reviewed corpus. The conclusion should instead report evidence-based findings from the dataset: dominant keywords, growth trends, leading countries/institutions, method clusters, and underdeveloped research directions.

Is the topic of the review discussed comprehensively in the context of the current literature?

No
Are all factual statements correct and adequately supported by citations?

No
Is the review written in accessible language?

Partly
Are the conclusions drawn appropriate in the context of the current research literature?

No

Competing Interests

No competing interests were disclosed.

Reviewer Expertise

Intersection of computational mechanics and applied AI, finite element modelling (Abaqus), structural verification, and developing Python-based automation for simulations, post-processing, and reporting.

I confirm that I have read this submission and believe that I have an appropriate level of expertise to state that I do not consider it to be of an acceptable scientific standard, for reasons outlined above.

Respond to this report

Responses (0)

[1] 1. Khaleel M, Ahmed A, Alsharif AH: Artificial Intelligence in Engineering. Brilliance: Research of Artificial Intelligence. 2023; 3: 32–42. Publisher Full Text Reference Source

[2] 2. Yüksel N, Börklü HR, Sezer HK, et al.: Review of artificial intelligence applications in engineering design perspective. Eng. Appl. Artif. Intell. 2023; 118: 105697. Publisher Full Text

[3] 3. Khanolkar P, Vrolijk A, Olechowski A: Mapping artificial intelligence-based methods to engineering design stages: a focused literature review. Artificial Intelligence for Engineering Design, Analysis and Manufacturing. 2023; 37. Reference Source

[4] 4. Alhakeem MRH, Ilham DN: Application of Artificial Intelligence in Mechanical Engineering. Brilliance: Research of Artificial Intelligence. 2022. Reference Source

[5] 5. Zhang F: Design and Implementation of Industrial Design and Transformation System Based on Artificial Intelligence Technology. Math. Probl. Eng. 2022; 2022: 1–9. Publisher Full Text Reference Source

[6] 6. Zou Q, Wu Y, Liu Z, et al.: Intelligent CAD 2.0. ArXiv. 2024; abs/2410.03759. Reference Source

[7] 7. Obaid AJ, Sharma S: Recent Trends and Development of Heuristic Artificial Intelligence Approach in Mechanical System and Engineering Product Design. Saudi J Eng Technol. 2020; 05: 86–93. Publisher Full Text Reference Source

[8] 8. Rossi L, Winands M, Butenweg C: Monte Carlo Tree Search as an intelligent search tool in structural design problems. Eng. Comput. 2021; 38: 3219–3236. Publisher Full Text Reference Source

[9] 9. Sidorenko DO, Gavaza KG, Starodubcev NO, et al.: Generative Design of Physical Objects using Modular Framework. Eng. Appl. Artif. Intell. 2022; 119: 105715. Reference Source

[10] 10. Singh MM, Chen X, Geyer P: Explainable AI for engineering design: A unified approach of systems engineering and component-based deep learning. Adv. Eng. Inform. 2021; 62: 102843. Reference Source

[11] 11. Alghazo M, Ahmed V, Bahroun Z: Exploring the applications of artificial intelligence in mechanical engineering education. Frontiers in Education. Frontiers Media SA; 2025; p. 1492308.

[12] 12. Málaga-Chuquitaype C: Machine Learning in Structural Design: An Opinionated Review. Front Built Environ. 2022. Reference Source

[13] 13. Elrefaie M, Qian J, Wu R, et al.: AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design. ArXiv. 2025; abs/2503.23315. Reference Source

[14] 14. Fallacara G, Fanti MP, Parisi F, et al.: AI-driven image generation for enhancing design in digital fabrication: urban furnishings in historic city centres. VIPERC. 2023. Reference Source

[15] 15. Mondal S, Goswami S: Rise of Intelligent Machines: Influence of Artificial Intelligence on Mechanical Engineering Innovation. Spectrum of Engineering and Management Sciences. 2024; 2: 46–55. Publisher Full Text Reference Source

[16] 16. Zou N, Wang Q, Li X: Practical Exploration of Simulation Technology Based on Artificial Intelligence in Engineering Design. Scientific Journal of Technology. 2024; 2: 46–55. Publisher Full Text Reference Source

[17] 17. El Naqa I, Murphy MJ: What Are Machine and Deep Learning?. Machine and Deep Learning in Oncology, Medical Physics and Radiology. Cham: Springer International Publishing; 2022; pp. 3–15. Publisher Full Text

[18] 18. Brisco R, Hay L, Dhami S: EXPLORING THE ROLE OF TEXT-TO-IMAGE AI IN CONCEPT GENERATION. Proceedings of the Design Society. 2023; 3: 1835–1844. Publisher Full Text Reference Source

[19] 19. Kamolov S: Machine learning methods in civil engineering: a systematic review. Annals of Mathematics and Computer Science. 2024; 21: 181–191. Publisher Full Text Reference Source

[20] 20. Payrebrune K, et al.: The impact of AI on engineering design procedures for dynamical systems. ArXiv. 2024; abs/2412.12230. Reference Source

[21] 21. Yang J, Liao J, Feng L: Artificial intelligence inspired freeform optics design: a review. ArXiv. 2024; abs/2410.03554. Reference Source

[22] 22. Rudolph S: On Some Artificial Intelligence Methods in the V-Model of Model-Based Systems Engineering. International Conference on Model-Driven Engineering and Software Development. 2024. Reference Source

[23] 23. Tolk A, Barry P, Doskey SC: Using modeling and simulation and artificial intelligence to improve complex adaptive systems engineering. International Journal of Modeling, Simulation, and Scientific Computing. 2022; 13(02): 2241004. Publisher Full Text

[24] 24. Shen Y, Yu P, Lu H, et al.: An AI-based virtual simulation experimental teaching system in space engineering education. Comput. Appl. Eng. Educ. 2021; 29(2): 329–338. Publisher Full Text

[25] 25. Zou Q, Wu Y, Liu Z, et al.: Intelligent CAD 2.0. Visual Informatics. 2024; 8: 1–12. Publisher Full Text

[26] 26. de Payrebrune KM , et al.: The impact of AI on engineering design procedures for dynamical systems. arXiv preprint arXiv:2412.12230. 2024.

[27] 27. Saini M: AI and its Application in CAD. Int J Adv Eng Manag. 2023; 5(4): 1874–1879.

[28] 28. Hunde BR, Woldeyohannes AD: Future prospects of computer-aided design (CAD)–A review from the perspective of artificial intelligence (AI), extended reality, and 3D printing. Results Eng. 2022; 14: 100478. Publisher Full Text

[29] 29. Balagopal PA: Impact of Artificial Intelligence on Mechanical Engineering: A Comprehensive Overview. Int J Innov Sci Res Technol. 2024; 9(7): 1829–1832.

[30] 30. Yoo S, Lee S, Kim S, et al.: Integrating deep learning into CAD/CAE system: generative design and evaluation of 3D conceptual wheel. Struct. Multidiscip. Optim. 2020; 64: 2725–2747. Reference Source

[31] 31. Chen C-H: Application of Multiple Deep Neural Networks to Multi-Solution Synthesis of Linkage Mechanisms. Machines. 2023; 11(11): 1018. Publisher Full Text

[32] 32. Yim NH, Ryu J, Kim YY: Big data approach for synthesizing a spatial linkage mechanism. 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE; 2023; pp. 7433–7439.

[33] 33. Röder B, Ebel H, Eberhard P: Towards intelligent design assistants for planar multibody mechanisms. PAMM. 2023; 23(4): e202300060. Publisher Full Text

[34] 34. Lee S, Kim J, Kang N: Deep Generative Model-based Synthesis of Four-bar Linkage Mechanisms with Target Conditions. arXiv preprint arXiv:2402.14882. 2024.

[35] 35. Gerstmayr J, Manzl P, Pieber M: Multibody models generated from natural language. Multibody Syst. Dyn. 2024; 62(2): 249–271. Publisher Full Text

[36] 36. Nurizada A, Purwar A: Transforming Hand-Drawn Sketches of Linkage Mechanisms Into Their Digital Representation. J. Comput. Inf. Sci. Eng. 2024; 24(1). Publisher Full Text

[37] 37. Deshpande S, Purwar A: A machine learning approach to kinematic synthesis of defect-free planar four-bar linkages. J. Comput. Inf. Sci. Eng. 2019; 19(2): 021004. Publisher Full Text

[38] 38. Hassan NA, Sada AY: AI Techniques in Engineering Design Review Data. Mendeley Data. 2026; V1. Publisher Full Text

A Bibliometric Analysis of the Applications of Artificial Intelligence Techniques to Engineering Design

Abstract

Keywords

1. Introduction

Figure 1. Presents the keyword search by occurrence.

2. Methodology

2.1 Bibliometric analysis

2.2 Literature retrieval

Table 1. Breakdown of the top 30 searches.

Figure 2. Bibliometric distribution of research output by country.

Table 2. Top 20 countries by research output on engineering design and AI. Table 2 presents the top 20 countries that engage in research related to engineering design and artificial intelligence techniques.

Figure 3. Institutional distribution of global research output.

Table 3. Bibliometric performance summary: Comparative analysis of publication output, citation impact, and relational link strength.

3. Overview on AI technologies in engineering design

3.1 Machine Learning (ML)

3.2 Deep learning

3.3 Simulation

4. Specific AI applications to engineering design

5. Conclusions and future directions

Data availability

References

Comments on this article Comments (0)

Open Peer Review

Comments on this article Comments (0)

Open Peer Review

Reviewer Status

Reviewer Reports

Comments on this article

Browse by related subjects

Competing Interests Policy

Stay Updated