Next Article in Journal
Simulating the Surface Solar Irradiance of Africa Using a Regional Climate Model: Influence of Vegetation-Runoff Coupled System
Previous Article in Journal
Electrospun Poly(Lactic Acid)-Chitosan Nanofibers for Wound Healing Application
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Engineering Proceedings
Volume 31
Issue 1
10.3390/ASEC2022-13823
engproc-logo
Submit to this Journal
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Proceeding Paper

Artificial Intelligence Implications in Engineering and Production †

by
Seemant Tiwari
Department of Electrical Engineering, Southern Taiwan University of Science and Technology, Tainan City 71005, Taiwan
†
Presented at the 3rd International Electronic Conference on Applied Sciences, 1–15 December 2022; Available online: https://asec2022.sciforum.net/.
Eng. Proc. 2023, 31(1), 16; https://doi.org/10.3390/ASEC2022-13823
Published: 7 December 2022
(This article belongs to the Proceedings of The 3rd International Electronic Conference on Applied Sciences)
Versions Notes

Abstract

:
Humans have undergone technological innovation in their daily personal lives as a result of the invention of the computer, but, afterward, the web, as well as we, carry on living in a technologically advanced world. Artificial intelligence (AI) is a term that we always keep hearing among computer scientists because we are all aware that it is a fast-expanding discipline in a multitude of areas. Numerous problems, including dynamic, unpredictable behaviors, and intricacy, are present in the architecture of research and production tools and procedures. Several research and engineering experts’ working methods have recently changed as a result of the development of larger datasets, fast processing speed, cloud technology, and artificial intelligence procedures. For researchers and producers, such techniques provide exhilarating, cutting-edge solutions to difficult problems. In contrast, artificial intelligence (AI) is a broad field. The availability of a wide range of concepts, strategies, and techniques makes it difficult to select the best AI approach for the correct technical or production industry and settings. Our examination of the works on numerous Automatic industrial claims and production through using suggested classification provided valuable understanding. Additionally, we identified plans for potential AI application investigation in the fields of engineering besides production.

1. Introduction

Artificial intelligence approaches have affected every project lifecycle in addition to individual human survival. A decent quantity of consideration has been given to sectors such as engineering, product engineering, examination, surveillance, management, repairs and upkeep of infrastructure, and item evaluations and testing [1]. Power systems can also benefit from artificial intelligence [2]. Moreover, with the assistance of artificial intelligence methods, experts’ volume to generate, source, and manage cutting-edge devices and tools in the health sector, health coverage, power, petroleum and natural gas, educational, aviation, production, and automotive has significantly increased in recent years [1]. By quickly identifying, warning of, and resolving faults, rationale computation approaches have significantly aided in the development of more fuel-efficient, larger capacity planes in the aviation industry as well as decreased assets availability and repair time and expenses. The globe continues to be in the initial stages of an improved production revolt powered by AI, despite the broad usage of artificial intelligence in tackling various technical and production difficulties. However, AI approaches such as deep learning and ML have made atypical analytical tools for analyzing large production data available, which is difficult to do with traditional methodologies [1]. In various technical disciplines, AI technologies have assisted in locating answers to challenges that are domain-specific [3]. It is commonly accepted that AI aids in reducing cycle time and trash, which has now significantly improved resource use in certain complex production situations [4].
Despite the advantages of AI approaches in engineering and production, the variety of these approaches presents difficulties to many production professionals and experts over which methodology to choose from the many available. As a result, this could prevent a sizable portion of subject-matter specialists from using AI approaches. A classification of recent breakthroughs in AI approaches and their use in the field of engineering and production was undertaken by numerous researchers to overcome this barrier and assist production operators and experts in selecting the appropriate AI instrument for the task at hand [5].
The research of exactly how to make systems-based methods that could previously just be accomplished by people is known as artificial intelligence [6]. Intelligence has advanced significantly over the years, resulting in altered lifestyles and consumption [7]. Advancement is now a major development approach for governments all over the world, helping to boost export performance while also increasing safety. Artificial intelligence (AI) is a multidisciplinary technique that integrates intelligence, computer vision, face recognition, human connection, storage systems, and judgment.
The residual portion of this work is structured as surveys: an overview of AI in addition to machine learning is given in Section 2. Section 3 explores the field of AI research. The usage of AI in engineering and production is shown in Section 4. Moreover, Section 5 summarizes the plan for further research. Section 6 is the conclusion.

2. Artificial Intelligence and Machine Learning

Developing a computer code or a robotic controlled by a system carrying out operations that generally need artificial intellect or critical thinking is the goal of artificial intelligence (AI), a comprehensive field of computer programming. AI is a multifaceted, interdisciplinary field of study focused on fields including data science, genetics, neurology, languages, and technology. The most popular method for achieving AI is machine learning, and deep learning is a particular kind of ML. A fundamental change is also brought about by ML and DL developments in virtually every area of the industrial, production, and technology sectors. Machine learning is based on the usage of algorithms that increases its effectiveness by using data to learn. Forecasting, cluster analysis, categorization, and wavelet transform are the four main essential kinds of issues that require machine learning to handle [8].
Computers and devices may adapt autonomously and become improved founded on their pieces of knowledge and appreciation of machine learning (ML). Typically, ML approaches are separated into two categories: supervised learning in addition to unsupervised learning. In SL (supervised learning), a labeled database (x, y) known as train data is provided to the method, and utilizing this information, one forms a model. The approach is then applied to address similar issues [9]. In contrast, UL (unsupervised learning) uses an unlabeled database to feed the method, which then builds a model. The model then attempts to derive predictions from the large data or find hidden trends [10].
Artificial intelligence uses have many benefits and have the potential to alter professional areas completely. However, on the other hand, there are certain drawbacks to artificial intelligence as well [11].

2.1. Benefits of AI

Operator error factor reduction or eradication: Artificial intelligence may assist in reducing the consequences of human error when technologies like infraction detection using weather forecast technologies, and other forecasting or video cameras are taken into consideration.
  • The capacity to make decisions quickly: Systems that use artificial intelligence techniques provide quicker and more useful solutions because of the methods they have and because they do not need to analyze emotions as people do.
  • Performing effectively and efficiently: Inside an enterprise, human-assisted computers can be utilized as individuals can run them efficiently. Client service software was supplemented by artificial intelligence. These technologies make it feasible to react to consumers’ inquiries and need whenever they arise, irrespective of the time.
  • Innovative new products or technologies: The medical profession regularly makes use of artificial intelligence. In regards to disease identification or treatment, enhancing the system that uses artificial intelligence can provide more efficient or unique alternatives than professionals.

2.2. AI Disadvantages

The following drawbacks pertain to artificial intelligence.
  • Joblessness: Automated factories now take the role of humans, thanks to advances in artificial intelligence techniques. This might result in a decline in the need for human labor.
  • Expenses: The artificial intelligence industry is continuously upgrading itself through new developments due to quick technological progress. Costs rise because it takes more money to undertake the necessary adjustments to the computer’s hardware and software to stay up with these developments.
  • Humans being sluggish: Humans become accustomed to being lazy as a result of the apps or systems that are managed by artificial intelligence in several facets of daily life.

3. Field of AI Research

Artificial intelligence is becoming more prevalent in our lives all the time and is still emerging in numerous industries. The relevant paragraphs list popular usage areas.
  • Robotics: Robotic systems are often effective that carry out manual processes autonomously. Furthermore, intelligent machines using artificial intelligence frequently obtain the capacity to decide on their own whether to accomplish an objective or carry out a function, in contrast to pre-programmed robotic systems. Clip inputs, movement, and material detectors, as well as numerous sensors created specifically for a given purpose, are all included in robotic applications. With the use of artificial intelligence techniques and programming, numerous activities are performed using inputs received from various instruments. Moreover, with the advancement of artificial intelligence technologies, robotic systems now have the intelligence needed to sense their surroundings and organize future actions by displaying individual behaviors [12].
  • Automatic Speech Recognition: The capacity of technology to understand the words we use, to analyze that understanding, and then transcribe it into words by adding commentary is known as naturally occurring language processing. Writings are typically utilized as input, together with voice recognition. These days, it serves a variety of purposes, including telecom services, interpretation software, and cellphone helper apps [13]. Voice recognition is the procedure of identifying the presenter’s voice patterns and translating those into oral language. It includes automated and precise translation into texts through keywords or expressions by converting the acoustically recorded transmitted data to a sequence of words. One of the most widely popular apps that makes usage speech recognition software is the spoken writing function in texting mobile apps [14].
  • Data Mining: The structured, interdisciplinary discipline is called an aspect of the study, and data mining is devoted to techniques for obtaining data from massive data sets that can be utilized to find novel, practical, and rational behaviors. Though some forms of neural network models or machine learning are employed in information discovery and data mining, the objectives are unique. Instead of developing a depiction that details the most important characteristics of the complete representative group, the challenge in this situation is to discover valuable information in a vast dataset [15].
  • The Identification of Patterns: The research of exactly how to create machines with perceptive ability is known as pattern classification. It focuses on the detection of both visual and aural trends, such as object classification, topography, pictures, and typefaces, and so on. It has numerous applications in everyday life as well as the army. The amount of usage of fuzzy statistical equations and neural network modeling has quickly increased over the years, increasingly displacing both classic forecasting methods and structured pattern-matching approaches [16].

4. Usage of AI in Engineering and Production

A collection of sophisticated computer algorithms make up artificial intelligence. The implications of artificial intelligence technologies include things such as a decrease in productivity and a decrease in people, alongside advantages such as cost savings, efficiency gains, safety assurance, technology, economics, medicine, defense, transportation, and forecasting, among other things. Advanced techniques typically utilize artificial intelligence to handle challenging issues in the areas. The finest place to use artificial intelligence is down below.
  • Uses in the Defense Industry: The innovation of artificial intelligence, which is advancing quickly and may have significant effects here in the area of national defense, is being attentively watched and developed by nations. Due to its combined computation and judgment capacities, artificial intelligence is employed to enhance key components of defense sectors [17]. In [18], elucidating the defense industry in terms of the realms of command and control was elucidated.
  • Medicine: As technology advances, medical advancements backed by artificial intelligence create workable solutions regarding medical applications. In several medical settings, artificial intelligence is used for diagnosis, therapy, and result prediction. Artificial intelligence’s application to medicine production [19]. In [20], discuss health monitoring.
  • Transport system: The advancements in artificial intelligence open up the previously unimaginable potential for the transport industry in addition to other industries, and they also pave the path for the creation of creative solutions to a wide range of problems. The first issues that occur in the mind when thinking about challenges are traffic problems, safety issues, air degradation, traffic noise, energy spent, and financial damage as a result of each of these. Studies are being carried out on a variety of topics using artificial intelligence, including removing potential traffic jams, growing consumer trust in journey times, lowering noise and air degradation, and increasing efficiency in the transport industry. By using it, we could manage things like car parking, predict accidents, and manage traffic [21]. Artificial intelligence (AI) is a very potent technology in the transport network due to its application in the fields of roadway and traffic monitoring [22].

5. A Future of Artificial Intelligence

Nowadays, artificial intelligence is used in a wide range of industries. Further research and improvement will proceed, the latest software approaches will be found, and new products will be developed. It is going to be able to create specialist programming tools that enable developers to create apps for intelligent systems as well as other types of artificial intelligence. Such advancements will happen not just in the computer industry but also in the technology domain. Intelligence systems will be created, and speech recognition capabilities will spread throughout numerous applications.
We may argue that deep and machine learning methods are presently some of the potent, intelligence instruments employed in intelligent engineering and production procedures. Future predictions indicate that their significance will increase. Additionally, AI’s interdisciplinary nature opens up a lot of possibilities. Coordination among several fields, including mechatronics, telecommunications, electrical and mechanical engineering, computer programming, then mathematics, which would be required to advance in the twenty-first century, poses a significant risk.
To provide a more accessible and then the on-processing solution for intelligent EM operation, computed intelligence, including deep learning algorithms, might well be extended into the Internet when computational capabilities, including cloud environment and data storage, are developed.

6. Conclusions

The paper provides a thorough analysis of AI with attention to relevant applications and issues. AI is a multidisciplinary field that includes knowledge, mathematics, perception, understanding, networks, and biology. It has already been utilized in the synthesis of information, pattern matching, computer vision, and naturally occurring language processing. Numerous programs have been developed, including autonomous computing, optimization techniques, understandings, and smart robotics.

Funding

This research received no external funding.

Institutional Review Board Statement

The research was carried out following the Helsinki declaration principles.

Informed Consent Statement

All subjects engaged in the study provided informed consent.

Data Availability Statement

The datasets used in this investigation are accessible from the author.

Conflicts of Interest

The author declares no conflict of interest.

References

  1. Aggour, K.S.; Gupta, V.K.; Ruscitto, D.; Ajdelsztajn, L.; Bian, X.; Brosnan, K.H.; Kumar, N.C.; Dheeradhada, V.; Hanlon, T.; Iyer, N.; et al. Artificial intelligence/machine learning in manufacturing and inspection: A GE perspective. MRS Bulletin. 2019, 44, 545–558. [Google Scholar] [CrossRef]
  2. Tiwari, S. Methodologies of artificial intelligence in power system. Int. Conf. Sustain. Eng. Technol.-Eng. Technol. Innov. Sustain. 2022, 1, 52–56. [Google Scholar]
  3. Hegde, J.; Rokseth, B. Applications of machine learning methods for engineering risk assessment—A review. Saf. Sci. 2020, 122, 104492. [Google Scholar]
  4. Bedbrook, C.N.; Yang, K.K.; Robinson, J.E.; Mackey, E.D.; Gradinaru, V.; Arnold, F.H. Machine learning-guided channelrhodopsin engineering enables minimally invasive optogenetics. Nat. Methods 2019, 16, 1176–1184. [Google Scholar] [CrossRef] [PubMed]
  5. Ardabili, S.; Mosavi, A.; Várkonyi-Kóczy, A.R. Systematic review of deep learning and machine learning models in biofuels research. Int. Conf. Glob. Res. Educ. 2019, 101, 19–32. [Google Scholar]
  6. Huang, B.; Huan, Y.; Xu, L.D.; Zheng, L.; Zou, Z. Automated trading systems statistical and machine learning methods and hardware implementation: A survey. Enterp. Inform. Syst. 2018, 13, 132–144. [Google Scholar] [CrossRef] [Green Version]
  7. Huang, C.; Cai, H.; Xu, L.; Xu, B.; Gu, Y.; Jiang, L. Data-driven ontology generation and evolution towards intelligent service in manufacturing systems. Future Gener. Comput. Syst. 2019, 101, 197–207. [Google Scholar] [CrossRef]
  8. Erhan, D.; Courville, A.; Bengio, Y.; Vincent, P. Why does unsupervised pre-training help deep learning? In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 13–15 May 2010; Volume 9, pp. 201–208. [Google Scholar]
  9. Sharma, R.; Kamble, S.S.; Gunasekaran, A.; Kumar, V.; Kumar, A. A systematic literature review on machine learning applications for sustainable agriculture supply chain performance. Comput. Operat. Res. 2020, 119, 104926. [Google Scholar] [CrossRef]
  10. Sharma, A.; Zhang, Z.; Rai, R. The interpretive model of manufacturing: A theoretical framework and research agenda for machine learning in manufacturing. Int. J. Produc. Res. 2021, 59, 4960–4994. [Google Scholar] [CrossRef]
  11. Khanzode, K.C.A.; Sarode, R.D. Advantages and disadvantages of artificial intelligence and machine learning: A literature review. Int. J. Libr. Inform. Sci. 2020, 9, 30–36. [Google Scholar]
  12. Vrontis, D.; Christofi, M.; Pereira, V.; Tarba, S.; Makrides, A.; Trichina, E. Artificial intelligence, robotics, advanced technologies and human resource management: A systematic review. Int. J. Hum. Res. Manag. 2020, 33, 1237–1266. [Google Scholar] [CrossRef]
  13. Maulud, D.H.; Zeebaree, S.R.; Jacksi, K.; Sadeeq, M.A.M.; Sharif, K.H. State of art for semantic analysis of natural language processing. Qubahan Acad. J. 2021, 1, 21–28. [Google Scholar] [CrossRef]
  14. Huang, X.; Baker, J.; Reddy, R. A historical perspective of speech recognition. Commun. ACM 2014, 57, 94–103. [Google Scholar] [CrossRef]
  15. Maimon, O.; Rokach, L. Introduction to knowledge discovery and data mining. In Data Mining and Knowledge Discovery Handbook; Springer: Boston, MA, USA, 2010; pp. 1–15. [Google Scholar]
  16. Yang, H.; Wen, J.; Wu, X.; He, L.; Mumtaz, S. An efficient edge artificial intelligence multipedestrian tracking method with rank constraint. IEEE Trans. Industr. Inform. 2019, 15, 4178–4188. [Google Scholar] [CrossRef]
  17. Meng, X.; Nie, L.; Song, J. Research on urban anti-terrorism intelligence perception system from the perspective of Internet of things application. Int. J. Electr. Eng. Educ. 2021, 58, 248–257. [Google Scholar] [CrossRef]
  18. Wang, F. Technology framework of the intelligent command and control system. In IOP Conference Series: Materials Science and Engineering; IOP Publishing Ltd.: Redcliffe Way, Bristol, UK, 2019; p. 677. [Google Scholar]
  19. Mak, K.K.; Pichika, M.R. Artificial intelligence in drug development: Present status and future prospects. Drug Disc. Today 2019, 24, 773–780. [Google Scholar] [CrossRef] [PubMed]
  20. Sun, L.; Shang, Z.; Xia, Y.; Bhowmick, S.; Nagarajaiah, S. ASCE. Review of bridge structural health monitoring aided by big data and artificial intelligence: From condition assessment to damage detection. J. Struct. Eng. 2020, 146, 04020073. [Google Scholar] [CrossRef]
  21. Abduljabbar, R.; Dia, H.; Bagloee, S.A. Applications of artificial intelligence in transport: An overview. Sustainability 2019, 11, 189. [Google Scholar] [CrossRef] [Green Version]
  22. Astarita, V.; Festa, D.C.; Giofrè, V.P. Mobile systems applied to traffic management and safety: A state of the art. Proc. Comput. Sci. 2018, 134, 407–414. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Tiwari, S. Artificial Intelligence Implications in Engineering and Production. Eng. Proc. 2023, 31, 16. https://doi.org/10.3390/ASEC2022-13823

AMA Style

Tiwari S. Artificial Intelligence Implications in Engineering and Production. Engineering Proceedings. 2023; 31(1):16. https://doi.org/10.3390/ASEC2022-13823

Chicago/Turabian Style

Tiwari, Seemant. 2023. "Artificial Intelligence Implications in Engineering and Production" Engineering Proceedings 31, no. 1: 16. https://doi.org/10.3390/ASEC2022-13823

Article Metrics

Back to TopTop