Research studies

Mechanical Engineering And Relationship Artificial Intelligence 

 

Prepared by the researche : Walaa A. Naje ‘ Technical Institute of Najaf, Al-Furat Al-Awsat Technical University, 54001, Najaf, Iraq

DAC Democratic Arabic Center GmbH

Journal of Iranian orbits : Thirty Issue – December 2025

A Periodical International Journal published by the “Democratic Arab Center” Germany – Berlin

Nationales ISSN-Zentrum für Deutschland
ISSN  2626-4927
Journal of Iranian orbits

:To download the pdf version of the research papers, please visit the following link

https://democraticac.de/wp-content/uploads/2025/12/%D9%85%D8%AC%D9%84%D8%A9-%D9%85%D8%AF%D8%A7%D8%B1%D8%A7%D8%AA-%D8%A5%D9%8A%D8%B1%D8%A7%D9%86%D9%8A%D8%A9-%D8%A7%D9%84%D8%B9%D8%AF%D8%AF-%D8%AB%D9%84%D8%A7%D8%AB%D9%88%D9%86-%D9%83%D8%A7%D9%86%D9%88%D9%86-%D8%A7%D9%84%D8%A3%D9%88%D9%84-%E2%80%93-%D8%AF%D9%8A%D8%B3%D9%85%D8%A8%D8%B1-2025.pdf

ABSTRACT

More and more fields within engineering are finding uses for artificial intelligence (AI), including environmental, mechanical, structural, electrical, and civil engineering. Examining the effects of AI technology on efficacy, action, and creativity is the goal of this review. Artificial intelligence (AI) improves project outcomes by automating repetitive tasks, enhancing design processes, making design work more efficient, and predicting when equipment will need maintenance. AI uses tools like generative design, predictive analytics, and machine learning to achieve these goals. Rapid iteration of design solutions is made possible by AI engineering’s generative design process, and real-time decisions are made possible by AI’s predictive analytics, which enhance both safety and resource utilization. Improved project planning and risk management, as well as energy optimization, have been the outcomes of the sophisticated use of artificial intelligence in modern infrastructure systems like smart grid, smart construction management, and information technology systems. More and more, real-time assessments of structure health and environmental conditions are being conducted using artificial intelligence and machine learning technologies. This leads to sustainable solutions and an improved infrastructure life cycle. Problems with security, ethics, and, most importantly, the lack of high-quality data needed to train AI are some of the downsides to using AI in engineering. Artificial intelligence technology is finding more and more uses as computing power increases. This article provides a concise overview of AI technology, covering its history, components, and development process. Additionally, the course delves into the notion of mechanical and electrical engineering and examines the connection between this field and AI technology. The article concludes with a brief overview of AI’s progress in mechanical defect diagnostics. I will demonstrate the specific application of artificial intelligence in mechanical engineering by using the defect diagnostics of hot forging presses as an example.

Introduction

The discipline of mechanical engineering is only one of several that has been profoundly affected by the advent of artificial intelligence (AI). When applied to mechanical engineering, AI has the ability to shake up established norms while opening up exciting new opportunities. Artificial intelligence (AI) has the potential to revolutionize mechanical engineering by enhancing operating efficiency, redesigning design approaches, and reshaping the manufacturing process. When it comes to designing systems and optimizing machinery, mechanical engineers have traditionally depended substantially on exact mathematical models, empirical data, and physical principles. Machines can now learn from massive datasets, model complicated situations and their consequences with different vector inputs, and systems may make judgments anonymously, all because to the arrival of AI technology. This has caused a paradigm change in industry and the society at large. Combining AI with engineering in a novel way paves the way for previously unimaginable possibilities. The use of mechatronic systems in mechanical engineering is on the rise due to technological and scientific advancements [1].

This shift incorporates AI. Software with the ability to reason and make decisions independently is known as artificial intelligence (AI). Improving productivity and quality of output is possible via mimicking the smart actions of experts. There has been significant progress in artificial intelligence systems since their inception. The mechanical and industrial sectors make extensive use of these systems for a variety of image processing, AI perception, pattern identification, and VR applications. Industry and mechanics are popular places to find automation and AI. Engineers’ approaches to project conception, design, and execution have undergone a sea change due to the incorporation of AI into mechanical engineering [2,3]. Traditional mechanical engineering is giving way to electronic mechanical engineering as a result of the ever-increasing sophistication of modern technologies. There has been steady progress in its degree of automation and intellectualization, and it has entered a new developmental stage; as a result, the intersection of AI technology with mechanical and electrical engineering is now a major focus. The realization of intelligent technology is based on the application of artificial intelligence technology, which in turn is based on the development of computer technology, which has enhanced computer technology via analysis. Automation control in mechanical engineering was the primary outcome of intelligent technology’s use in electrical and mechanical engineering. AI applications in these fields involve not just computer technology but also combines with information technology, psychology, linguistics and other knowledge [4,5].

Artificial intelligence (AI) goes beyond mundane tasks in engineering by automating specialized algorithms and models that enhance data-based decision-making. Engineers can now extract information from massive datasets with unprecedented accuracy, which completely changes the game for conventional engineering practice. The engineering field is already making use of AI to improve efficiency across the board by forecasting the need for equipment maintenance in various sectors and building supply chains. The development of solutions, methodologies, or platforms for the deployment of AI systems that will fulfil particular objectives has become the primary thrust in AI engineering, a sub-discipline of engineering.

While traditional engineering fields put a premium on algorithm creation, this subfield is equally concerned with finding ways to incorporate algorithms into preexisting engineering practices. There is a growing subset of engineers focused on artificial intelligence (AI) and their use of smart systems in several fields, including civil, structural, electrical, and mechanical engineering [5,6]. The usage of artificial neural networks (ANN) is on the rise across the board in engineering, from computer science and mathematics to mechanical engineering and beyond. It is an example of an adaptive based programming system used in engineering. In general, ANN [7] is a new approach to processing information. Its core principle is derived from current neuroscience studies that attempt to deduce the basic features of information processing from the way the human brain works by integrating various parallel, segmental, and simulation-based approaches [8].

A number of recent studies [9-16] show that ANNs, which are based on intelligent structure, design, and optimization, have made great strides in mechanical engineering. Artificial neural networks (ANNs) are a powerful computational tool for modelling the relationships between processes and the variables that affect them. The general structure of mechanically based equipment has become more complicated due to the fast development and application of technology. On top of that, it’s fully automated. In mechanical engineering, ANN is now highly regarded [17]. Several branches of mechanical engineering have benefited from its cutting-edge technologies, including machine design, production, and operation. In this paper, we take a look at how artificial neural networks (ANNs) are being used in mechanical engineering for things like intelligent machine fault diagnosis, mechanical structure analysis, system design, and optimization. The sequence of this review is as follows: In Module 2, the architecture and link between AI and mechanical engineering are fully illustrated. Module 3 delves into the methodology of the Artificial Neural Network. In Module 4, we learnt about the many ANNs used in the mechanical field. Use of artificial neural networks (ANNs) in mechanical engineering is detailed in Module 5, including intelligent defect diagnosis, mechanical structure analysis.

  1. What Is AI

Machines that can learn to act and think like humans are known as artificial intelligence (AI). Basically, it’s when computers are taught to mimic human intelligence through learning and behaviour. Artificial intelligence (AI) encompasses a wide variety of tools and methods, from models and programs to data approaches and algorithms. Some examples of AI-based tasks include translating languages, visual perception, decision-making, and speech recognition. Machines and computers equipped with artificial intelligence (AI) may mimic human intellect in areas such as learning, understanding, problem solving, decision making, creativity, and autonomy. Artificial intelligence (AI) enabled apps and devices can detect and recognize items. They are capable of comprehending and reacting to spoken words. With the right knowledge and experience, they can grow. Users and specialists can receive thorough suggestions from them. They are capable of autonomous behavior, doing away with the requirement for human intellect or involvement (a self-driving automobile is a prime example of this). Generative artificial intelligence (gen AI) is a system that can generate new information, such as text, photographs, and videos, and it will occupy the majority of AI-related attention in 2024. Generative AI tools are built on top of machine learning (ML) and deep learning, therefore understanding these technologies is crucial for properly grasping generative AI.

  1. Key components of AI scope include:
  2. Machine Learning: A subset of artificial intelligence approaches, machine learning allows computers to gradually improve their performance based on historical data and new information gathered over time, all without human intervention or code. Machine learning, which is often implemented as algorithms, is able to analyze data for patterns and draw conclusions.
  3. Deep Learning: utilized in complex situations is a subfield of machine learning that analyzes massive amounts of data by means of multi-layer neural networks. Deep learning has been widely utilized for applications like image and speech recognition.
  4. Expert System: Expert system (ES) is another important branch of artificial intelligence research [18]. It will explore the general way of thinking into the use of area of expertise to address certain challenges. Expert systems (ES) will put AI research into practice. An ES is a computer intelligent program system that draws on the knowledge and experience of specialists in a particular field, as well as AI reasoning techniques, to solve and mimic complex problems that are typically solved by humans. A knowledge base, database, reasoning machine, interpretation mechanism, knowledge acquisition, and user interface are the essential components of an expert system, as illustrated in Figure 1.

Figure 1: The basic structure of the expert system

  1. Natural Language Processing : Machine learning is a powerful branch of artificial intelligence that allows computers to comprehend, interpret, and even create new language. The techniques used in natural language processing (NLP) enable virtual assistants, translation assistance, and sentiment analysis, all of which are crucial in modern life.
  2. Robotics: Robotics is a key component of AI approaches as it allows robots to mimic environments, make decisions, and automatically carry out certain jobs. It finds extensive use in fields like as industrial automation, service robots, and healthcare assistants. The fast transformation of businesses and organizations by AI and its approaches is having far-reaching and enduring effects on society as a whole. Many industries stand to benefit greatly from the use of AI technology; they include healthcare, banking, transportation, and entertainment, among many others.
  3. Deep Learning: used in advanced scenario is a form of machine learning, that uses neural networks in multiple layers to analyse vast amount of data. Major use of deep learning has been seen in tasks such as image and speech recognition.

  1. Areas AI Can Be Deployed In Mechanical (Engineer Field)

The revolutionary impact of artificial intelligence (AI) on mechanical engineering will reverberate across all sectors that rely heavily on the field. Businesses may benefit from AI in mechanical engineering by improving their decision-making, creativity, and efficiency

Here are some key ways AI is aligned with engineering disciplines:

  1. Design and Optimization: An essential part of mechanical engineering is the design process, which AI might assist automate and simplify. By sifting through enormous datasets, machine learning algorithms are able to generate and propose design alternatives, optimize parameters, and forecast performance outcomes, outperforming more traditional methods. As indicated in their study, the use of AI algorithms has improved design optimization, giving engineers powerful tools for optimizing mechanical designs [19]. By rapidly iterating through design concepts utilizing AI-powered design optimization methodologies, mechanical engineering teams may minimize the time it takes to bring new products to market, which speeds up innovation cycles [20].
  2. Predictive Maintenance: Maintenance is highly valued in the field of mechanical engineering. Apps driven by artificial intelligence can now monitor machinery health in real time, made possible by an abundance of sensors and data. By identifying potential problems and taking preventative measures, engineers may reduce maintenance expenses and downtime through the use of predictive maintenance. Predictive maintenance systems and condition monitoring powered by artificial intelligence are light years ahead of the competition, which often rely on set schedules or intervene in response to equipment failures. To prevent future mistakes, these AI-powered models combine real-time sensor data and sophisticated machine learning algorithms [21].
  3. Manufacturing Automation: Robots and smart systems may be used to automate industrial processes with AI-powered applications. Robots powered by AI models are capable of performing tasks with great accuracy and flexibility. Overall, this method helps with quality control and makes manufacturing much more efficient.
  4. Smart Systems and IoT: The need for internet-based control is also justified by the fast expansion of internet-connected smart devices.Artificial intelligence (AI) improves the engineering and application capabilities of IoT devices. Operating efficiency may be achieved via the use of machine learning algorithms that evaluate data collected from linked devices’ sensors in order to manage the inputs and, in some instances, improve the output.
  5. Simulation and Modeling: With the help of AI, mechanical engineers can model processes and anticipate their results, which is a crucial component of the field. Engineers will be able to save time and effort by using Machine Learning algorithms to model complicated situations, predict actions, and adjust settings to achieve desired results before production begins. Structural analysis, fluid dynamics, and electromagnetics are just a few of the engineering fields that make good use of modeling and simulation.
  6. Decision Support Systems: When it comes to making smart business choices, AI may be a huge assistance. By analyzing datasets, finding trends, and providing suggestions for process improvement, optimum resource allocation, and project management, engineering apps powered by AI may assist teams and individuals in making data-driven decisions.
  7. Natural Language Processing (NLP): Automation of knowledge base and documentation-related processes, together with insight extraction, is one potential use of natural language processing technology. Mechatronic systems are rapidly replacing traditional methods in mechanical engineering as a result of technological and scientific advancements. Ai is used in this modification. Computer programs with “artificial intelligence” (AI) capabilities may reason and act independently. Our output quality and productivity may be greatly enhanced if we can learn to mimic the techniques used by the experts. Since their inception, AI systems have made tremendous strides. These systems have extensive use in the mechanical and industrial sectors, particularly in the areas of machine vision, pattern recognition, AI perception, and image processing. Automation and artificial intelligence are crucial in mechanics and industry. There is a The simulation industry’s modeling and simulation languages and environments are flexible enough to manage the specifics of each stage of the design process. Languages, for instance, ought to facilitate the ease of updating and expanding models in order for them can accommodate all the analyses done during design. Additionally, for designers and analysts with domain expertise to efficiently cooperate on the creation of complex artefacts, it is important that the simulation software be well-integrated with the design tools [23]

  1. Application of Artificial Intelligence in Mechanical Engineering

Artificial intelligence is increasingly being used for failure diagnostics in mechanical engineering [24, 25]. In order to find errors, several AI-based methods include rule-based reasoning (RBR), case-based reasoning (CBR), and fault-based tree fault diagnostics. Our mechanical flaw detection system utilizes RBR and CBR reasoning and is built using the typical components and principles of an expert system. Everything is laid out in Figure 2. The system is comprised of a learning system, an expert system-machine interface, a database of fault diagnostic rules and diagnostics, a machine for reasoning about faults, knowledge processing, and an interpreter for fault diagnostic procedures. The heart of the diagnostic system is the man-machine interface, which allows the operator to enter the online data that the machine is monitoring. Secondly, the positive reasoning process will trigger the appropriate rules inside the reasoning machine, which will then provide diagnostic findings. After that, it will utilize an algorithm to retrieve the case from the database after consulting with diagnostic specialists. In the next step, it will choose the most comparable example, calculate the degree of similarity using the historical case, and successfully identify the machinery problem. Lastly, by adding additional instances, the expert diagnosis system will be much better.

  1. Application of Fault Diagnosis to Hot Film Forging Press

It is not uncommon for hot forging presses to experience lubrication failure, stuffy cars, high motor current, and the slider halting outside the top dead center, among other common serious concerns. A combination of the hot forging press fault detection method with rule reasoning and case reasoning might help narrow down the many possible reasons of these failures. To identify the manufacturing process defect with the hot forging press, rule reasoning and case reasoning are used as a foundation. The system calculates the failure rate by using the relevant rule reasoning and case reasoning from the case library.

Figure 2:  The overall structure of the system

  1. Conclusion

In addition to discussing AI’s history and current state, this article also delves into the field’s connections to mechanical and electrical engineering. Additionally, it provides a concise overview of the pertinent mechanical engineering applications. In light of recent advances in knowledge, distributed AI, and other computer technologies, as well as extensive use of intelligent technology across mechanical systems, both theoretical and practical studies have shown that AI is becoming increasingly useful in this and other domains. The equipment business is becoming more and more competitive, thus a hybrid intelligent system based on design, monitoring, control, and diagnostics is being considered.

A new focus of study will be expert systems, neural networks, and fuzzy logic to enhance its intelligent control. There is a lot of hope for these applications. This research provides an in-depth examination of the many forms and applications of AI, as well as its connections to mechanical engineering and the design and detection of mechanical faults. An outline the specific applications of AI in mechanical engineering is provided in this article. Several applications, such as mechanical design, diagnostic systems, mechanical structure analysis, and error detection, are covered in detail. All of mechanical engineering, according to this research, makes extensive use of intelligent techniques based on artificial intelligence. The study also concludes that mechanical engineering is a natural fit for the incorporation of several other AI-based technologies that may improve mechanical systems. To further the current state of mechanical engineering, future work will propose a hybrid-based intelligent design of mechanical systems using AI-based systems like neural networks and fuzzy logic for observation, control, and error detection.

References

[1] Srivastava, Sambhrant & Kumar, Vijay & Singh, Saurabh & Yadav, Pankaj & Singh, Brihaspati & Bhaskar, Amit. (2024). A Review on Application of Artificial Intelligence in Mechanical Engineering. 10.4018/979-8-3693-5271-7.ch002.

[2] Mondal, Surajit & Goswami, Shankha. (2024). Rise of Intelligent Machines: Influence of Artificial Intelligence on Mechanical Engineering Innovation. Spectrum of Engineering and Management Sciences. 2. 46-55. 10.31181/sems1120244h.

[3] Cioffi, R., Travaglioni, M., Piscitelli, G., Petrillo, A., & De Felice, F. (2020). Artificial intelligence and machine learningapplications in smart production: Progress, trends, and directions. Sustainability, 12(2), 492.https://doi.org/10.3390/su12020492.

[4] P Norvig, SJ Russell. Artificial intelligence: a modern approach [J]. Applied Mechanics & Materials, 2003, 263 (5): 2829-2833.

 [5] RA Brooks. Intelligence without representation [J]. Artificial Intelligence, 1991, 47 (1–3): 139-159.

 [6] DE Goldberg, JH Holland. Genetic algorithms and machine learning [J]. Machine Learning, 1988, 3 (2): 95-99.

 [7] B Chandrasekaran. Generic tasks in knowledge-based reasoning: High-level building blocks for expert system design [J]. IEEE Expert, 1986, 1 (3): 23-30.

 [8] MH Hassoun. Fundamentals of artificial neural networks [J]. Proceedings of the IEEE, 1996, 84(6): 906.

 [9] Y Lecun, Y Bengio, G Hinton. Deep learning [J]. Nature, 2015, 521 (7553): 436-444.

[10] W Bolton. Mechatronics electronic control systems in mechanical and electrical engineering [J]. Fish Physiology & Biochemistry, 2009, 35 (3): 385-398.

 [11] H Yang, J Mathew, L Ma. Intelligent diagnosis of rotating machinery faults – A review [M]. Pattern Recognition & Data Mining, 2002.

[12]Arinez, J. F., Chang, Q., Gao, R. X., Xu, C., & Zhang, J. (2020). Artificial intelligence in advanced manufacturing: Current status and future outlook. Journal of Manufacturing Science and Engineering, 142(11), 110804.

 [13]Liu, J., Chang, H., Forrest, J. Y. L., & Yang, B. (2020). Influence of artificial intelligence on technological innovation: Evidence from the panel data of china’s manufacturing sectors. Technological Forecasting and Social Change, 158,120142.

 [14] Chang, C. W., Lee, H. W., & Liu, C. H. (2018). A review of artificial intelligence algorithms used for smart machine tools. Inventions, 3(3), 41.

 [15] Rodriguez-Rodriguez, I., Rodriguez, J. V., Shirvanizadeh, N., Ortiz, A., & Pardo-Quiles, D. J. (2021). Applications ofartificial intelligence, machine learning, big data and the internet of things to the COVID-19 pandemic: Ascientometric review using text mining. International Journal of Environmental Research and Public Health, 18(16),8578.

 [16] Hoosain, M. S., Paul, B. S., & Ramakrishna, S. (2020). The impact of 4IR digital technologies and circular thinkingon the United Nations sustainable development goals. Sustainability, 12(23), 10143.

 [17] Al-Gerafi, M. A., Goswami, S. S., Khan, M. A., Naveed, Q. N., Lasisi, A., AlMohimeed, A., & Elaraby, A. (2024).Designing of an effective e-learning website using inter-valued fuzzy hybrid MCDM concept: A pedagogicalapproach. Alexandria Engineering Journal, 97, 61-87.

 [18] Soori, M., Arezoo, B., & Dastres, R. (2023). Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cognitive Robotics.

 [19] Mohan, T. R., Roselyn, J. P., Uthra, R. A., Devaraj, D., & Umachandran, K. (2021). Intelligent machine learning based total productive maintenance approach for achieving zero downtime in industrial machinery Computers &Industrial Engineering, 157, 107267.

[20] Jenis, J., Ondriga, J., Hrcek, S., Brumercik, F., Cuchor, M., & Sadovsky, E. (2023). Engineering applications of artificialintelligence in mechanical design and optimization. Machines, 11(6), 577.

 [21] Dixon, J. R. (1986, August). Artificial intelligence and design: a mechanical engineering view. In Proceedings of the Fifth AAAI National Conference on Artificial Intelligence (pp. 872-877).

[22] Al-Bahrani, M., & Cree, A. (2021). In situ detection of oil leakage by new self-sensing nanocomposite sensor containing MWCNTs. Applied Nanoscience, 11(9), 2433-2445.

[23] Quintana, G., Garcia-Romeu, M. L., & Ciurana, J. (2011). Surface roughness monitoring application based on artificial neural networks for ball-end milling operations. Journal of Intelligent Manufacturing, 22(4), 607-617.

[24] Al-Abboodi, H., Fan, H., Mhmood, I. A., & Al-Bahrani, M. (2022). The dry sliding wear rate of a Fe-based amorphous coating prepared on mild steel by HVOF thermal spraying. Journal of Materials Research and Technology, 18, 1682-1691.

[25] Meesad, P., & Yen, G. G. (2000). Pattern classification by a neurofuzzy network: application to vibration monitoring. ISA transactions, 39(3), 293-308.

5/5 - (1 صوت واحد)

المركز الديمقراطي العربي

مؤسسة بحثية مستقلة تعمل فى إطار البحث العلمي الأكاديمي، وتعنى بنشر البحوث والدراسات في مجالات العلوم الاجتماعية والإنسانية والعلوم التطبيقية، وذلك من خلال منافذ رصينة كالمجلات المحكمة والمؤتمرات العلمية ومشاريع الكتب الجماعية.

مقالات ذات صلة

زر الذهاب إلى الأعلى