Artificial intelligence in industry: Difference between revisions
No edit summary Tag: Reverted |
Restored revision 1252473506 by Beepboopbwaph (talk): Unsourced, promo, and likely AI-generated |
||
| (44 intermediate revisions by 30 users not shown) | |||
| Line 1: | Line 1: | ||
{{short description|Overview of the use of artificial intelligence in industry}} |
{{short description|Overview of the use of artificial intelligence in industry}} |
||
{{Artificial intelligence}} |
|||
'''Industrial artificial intelligence''', or '''industrial AI''', usually refers to the application of [[artificial intelligence]] to industry |
'''Industrial artificial intelligence''', or '''industrial AI''', usually refers to the application of [[artificial intelligence]] to industry and business. Unlike general artificial intelligence which is a frontier research discipline to build computerized systems that perform tasks requiring human intelligence, industrial AI is more concerned with the application of such technologies to address industrial pain-points for customer value creation, productivity improvement, cost reduction, site optimization, predictive analysis<ref>{{cite web|title=Reducing downtime using AI in Oil and Gas|url=https://tech27.com/resources/reducing-downtime-using-ai-iot-in-oil-gas-exploration-and-production/|website=Tech27}}</ref> and insight discovery.<ref>{{cite news|last1=Sallomi|first1=Paul|title=Artificial Intelligence Goes Mainstream|url=http://deloitte.wsj.com/cio/2015/07/29/artificial-intelligence-goes-mainstream/|newspaper=WSJ|publisher=The Wall Street Journal - CIO Journal - Deloitte|access-date=9 May 2017}}</ref> |
||
| ⚫ | Artificial intelligence and [[machine learning]] have become key enablers to leverage data in production in recent years due to a number of different factors: More affordable sensors and the automated process of data acquisition; More powerful computation capability of computers to perform more complex tasks at a faster speed with lower cost; Faster connectivity infrastructure and more accessible cloud services for data management and computing power outsourcing.<ref name=":5">{{cite web|last1=Schatsky|first1=David|last2=Muraskin|first2=Craig|last3=Gurumurthy|first3=Ragu|title=Cognitive technologies: The real opportunities for business|url=http://www2.deloitte.com/tr/en/pages/technology-media-and-telecommunications/articles/cognitive-technologies.html|publisher=Deloitte Review}}</ref> |
||
== History == |
|||
The concept of artificial intelligence was initially proposed in the 1940s,<ref name=":1" /> and the idea of improving productivity and gaining insights through smart analytics and modelling is not new. Artificial Intelligence and [[Knowledge-based systems|Knowledge-Based systems]] have been an active research branch of artificial intelligence for the entire product life cycle for product design, production planning, distribution, and field services.<ref>{{cite journal|last1=Fox|first1=Mark|title=Industrial Applications of Artificial Intelligence|journal=Robotics|date=1986|volume=2|issue=4|pages=301–311|doi=10.1016/0167-8493(86)90003-3}}</ref> E-manufacturing systems and e-factories<ref>{{cite journal|last1=Waurzyniak|first1=Patrick|title=Moving towards e-factory|journal=SME Manufacturing Magazine}}</ref> did not use the term “AI,” but they scale up modeling of engineering systems to enable complete integration of elements in the manufacturing eco-system for smart operation management. |
|||
| ⚫ | |||
== Categories == |
== Categories == |
||
Possible applications of industrial AI and machine learning in the production domain can be divided into seven application areas:<ref name=":1">{{Cite book |last1=Krauß |first1=J. |last2=Hülsmann |first2=T. |last3=Leyendecker |first3=L. |last4=Schmitt |first4=R. H. |title=Production at the Leading Edge of Technology |chapter=Application Areas, Use Cases, and Data Sets for Machine Learning and Artificial Intelligence in Production |date=2023 |editor-last=Liewald |editor-first=Mathias |editor2-last=Verl |editor2-first=Alexander |editor3-last=Bauernhansl |editor3-first=Thomas |editor4-last=Möhring |editor4-first=Hans-Christian |chapter-url=https://link.springer.com/chapter/10.1007/978-3-031-18318-8_51 |series=Lecture Notes in Production Engineering |language=en |location=Cham |publisher=Springer International Publishing |pages=504–513 |doi=10.1007/978-3-031-18318-8_51 |isbn=978-3-031-18318-8}}</ref> |
|||
Technology alone never creates any business value if the problems in industry are not well studied. The major categories which industrial AI may contribute to include; product and service innovation, process improvement, and insight discovery.<ref name=":5" /> |
|||
* Market & Trend Analysis |
|||
[[Cloud Foundry]] service platforms widely embed the artificial intelligent technologies.<ref name=":2">{{cite web|title=Predix|url=https://www.ge.com/digital/predix|access-date=9 May 2017|publisher=General Electric}}</ref><ref>{{cite web|title=IBM Bluemix|url=https://www.ibm.com/cloud-computing/bluemix/|access-date=9 May 2017|publisher=IBM}}</ref> [[Cyber manufacturing|Cybermanufacturing]] systems also apply [[predictive analytics]] and cyber-physical modeling to address the gap between production and machine health for optimized productivity.<ref name=":3">{{cite web|title=Cybermanufacturing Systems|url=https://www.nsf.gov/funding/pgm_summ.jsp?pims_id=505291|access-date=9 May 2017|website=National Science Foundation}}</ref> |
|||
* Machinery & Equipment |
|||
* Intralogistics |
|||
* Production Process |
|||
* Supply Chain |
|||
* Building |
|||
* Product |
|||
[[File:Taxonomy of Application Areas.png|thumb|653x653px|Taxonomy of application areas and application scenarios for machine learning and artificial intelligence in production]] |
|||
=== Product applications for user value creation === |
|||
Each application area can be further divided into specific application scenarios that describe concrete AI/ML scenarios in production. While some application areas have a direct connection to production processes, others cover production adjacent fields like logistics or the factory building.<ref name=":1" /> |
|||
An example from the application scenario ''Process Design & Innovation'' are [[collaborative robots]]. Collaborative robotic arms are able to learn the motion and path demonstrated by human operators and perform the same task.<ref>{{cite web|title=What Does Collaborative Robot Mean ?|url=http://blog.robotiq.com/what-does-collaborative-robot-mean|access-date=9 May 2017}}</ref> [[Predictive maintenance|Predictive]] and [[preventive maintenance]] through data-driven [[machine learning]] are exemplary application scenarios from the ''Machinery & Equipment'' application area.<ref name=":1" /> |
|||
Industrial AI can be embedded to existing products or services to make them more effective, reliable, safer, and to enhance their longevity.<ref name=":5" /> The automotive industry, for example, uses computer vision to avoid accidents and enable vehicles to stay in lane, facilitating safer driving. In manufacturing, one example is the prediction of blade life for self-aware [[Bandsaw|band saw]] machines, so that users will be able to rely on evidence of degradation rather than experience, which is safer, will extend blade life, and build up blade usage profile to help blade selection.<ref>{{cite web|title=【世界翻轉中】不怕機器翻臉 感應器讀懂它的心！ - YouTube|url=https://www.youtube.com/watch?v=uFlmZgbbWBA|website=Youtube|access-date=9 May 2017}}</ref> |
|||
| ⚫ | |||
=== Process applications for productivity improvement === |
|||
In contrast to entirely virtual systems, in which ML applications are already widespread today, real-world production processes are characterized by the interaction between the virtual and the physical world. Data is recorded using sensors and processed on computational entities and, if desired, actions and decisions are translated back into the physical world via actuators or by human operators.<ref>{{Cite journal |last1=Monostori |first1=L. |last2=Kádár |first2=B. |last3=Bauernhansl |first3=T. |last4=Kondoh |first4=S. |last5=Kumara |first5=S. |last6=Reinhart |first6=G. |last7=Sauer |first7=O. |last8=Schuh |first8=G. |last9=Sihn |first9=W. |last10=Ueda |first10=K. |date=2016-01-01 |title=Cyber-physical systems in manufacturing |url=https://www.sciencedirect.com/science/article/pii/S0007850616301974 |journal=CIRP Annals |volume=65 |issue=2 |pages=621–641 |doi=10.1016/j.cirp.2016.06.005 |issn=0007-8506}}</ref> This poses major challenges for the application of ML in production engineering systems. These challenges are attributable to the encounter of process, data and model characteristics: The production domain's high reliability requirements, high risk and loss potential, the multitude of heterogeneous data sources and the non-transparency of ML model functionality impede a faster adoption of ML in real-world production processes. |
|||
Automation is one of the major aspects in process applications of industrial AI.<ref name=":5" /> With the help of AI, the scope and pace of automation have been fundamentally changed.<ref>{{cite journal|last2=Chui|first2=Michael|last3=Miremadi|first3=Mehdi|last4=Bughin|first4=Jacques|last5=George|first5=Katy|last6=Willmott|first6=Paul|last7=Dewhurst|first7=Martin|date=2017|title=A Future that Works: Automation, Employment, and Productivity|url=http://www.mckinsey.com/~/media/McKinsey/Global%20Themes/Digital%20Disruption/Harnessing%20automation%20for%20a%20future%20that%20works/MGI-A-future-that-works-Executive-summary.ashx|last1=Manyika|first1=James|access-date=9 May 2017}}</ref> AI technologies boost the performance and expand the capability of conventional AI applications. An example is the [[collaborative robots]]. Collaborative robotic arms are able to learn the motion and path demonstrated by human operators and perform the same task.<ref>{{cite web|title=What Does Collaborative Robot Mean ?|url=http://blog.robotiq.com/what-does-collaborative-robot-mean|access-date=9 May 2017}}</ref> AI also automates the process that used to require human participation. An example is the Hong Kong subway, where an AI program decides the distribution and job scheduling of engineers with more efficiency and reliability than human counterparts do. |
|||
[[File:Challenges for Machine Learning in Production.png|left|thumb|641x641px|The challenges for ML applications in production engineering result from the encounter of process, data and ML model characteristics]] |
|||
In particular, production data comprises a variety of different modalities, semantics and quality.<ref name=":2">{{Cite journal |last1=Wuest |first1=Thorsten |last2=Weimer |first2=Daniel |last3=Irgens |first3=Christopher |last4=Thoben |first4=Klaus-Dieter |date=January 2016 |title=Machine learning in manufacturing: advantages, challenges, and applications |journal=Production & Manufacturing Research |language=en |volume=4 |issue=1 |pages=23–45 |doi=10.1080/21693277.2016.1192517 |s2cid=52037185 |issn=2169-3277|doi-access=free }}</ref> Furthermore, production systems are dynamic, uncertain and complex,<ref name=":2" /> and engineering and manufacturing problems are data-rich but information-sparse.<ref>{{Cite journal |last=Lu |first=Stephen C-Y. |date=1990-01-01 |title=Machine learning approaches to knowledge synthesis and integration tasks for advanced engineering automation |url=https://dx.doi.org/10.1016/0166-3615%2890%2990088-7 |journal=Computers in Industry |volume=15 |issue=1 |pages=105–120 |doi=10.1016/0166-3615(90)90088-7 |issn=0166-3615}}</ref> Besides that, due the variety of use cases and data characteristics, problem-specific data sets are required, which are difficult to acquire, hindering both practitioners and academic researchers in this domain.<ref name=":3">{{Cite journal |last1=Jourdan |first1=Nicolas |last2=Longard |first2=Lukas |last3=Biegel |first3=Tobias |last4=Metternich |first4=Joachim |date=2021 |title=Machine Learning For Intelligent Maintenance And Quality Control: A Review Of Existing Datasets And Corresponding Use Cases |url=https://www.repo.uni-hannover.de/handle/123456789/11367 |doi=10.15488/11280}}</ref> |
|||
=== Process and Industry Characteristics === |
|||
Another aspect of process applications is the modeling large-scale systems.<ref name=":5" /> [[Cyber manufacturing|Cybermanufacturing]] systems are defined as a manufacturing service system that is networked and resilient to faults by evidence-based modeling and data-driven [[deep learning]].<ref name=":3" /> Such a system deals with large and usually geographically distributed assets, which is hard to be modeled via conventional individual-asset physics-based model. With machine learning and optimization algorithms, a bottom-up framework considering machine health can leverage large samples of assets and automate the operation management, spare part inventory planning, and maintenance scheduling process. |
|||
The domain of production engineering can be considered as a rather conservative industry when it comes to the adoption of advanced technology and their integration into existing processes. This is due to high demands on reliability of the production systems resulting from the potentially high economic harm of reduced process effectiveness due to e.g., additional unplanned [[downtime]] or insufficient product qualities. In addition, the specifics of machining equipment and products prevent area-wide adoptions across a variety of processes. Besides the technical reasons, the reluctant adoption of ML is fueled by a lack of IT and data science expertise across the domain.<ref name=":1" /> |
|||
=== Data Characteristics === |
|||
=== Insight applications for knowledge discovery === |
|||
The data collected in production processes mainly stem from frequently sampling sensors to estimate the state of a product, a process, or the environment in the real world. Sensor readings are susceptible to noise and represent only an estimate of the reality under uncertainty. Production data typically comprises multiple distributed data sources resulting in various data modalities (e.g., images from visual quality control systems, time-series sensor readings, or cross-sectional job and product information). The inconsistencies in data acquisition lead to low [[signal-to-noise ratio]]s, low data quality and great effort in data integration, cleaning and management. In addition, as a result from mechanical and chemical wear of production equipment, process data is subject to various forms of [[Concept drift|data drifts]]. |
|||
Industrial AI can also be used for [[knowledge discovery]] by identifying insights in engineering systems.<ref name=":5" /> In aviation and aeronautics, AI has been playing a vital role in many critical areas, one of which is safety assurance and root cause. NASA is trying to proactively manage risks to aircraft safety by analyzing flight numeric data and text reports in parallel to not only detect anomalies but also relate it to the causal factors. This mined insight of why certain faults happen in the past will shed light on predictions of similar incidents in the future and prevent problems before they occur.<ref>{{cite web|last1=Laskowski|first1=Nicole|title= NASA uses text analytics to bolster aviation safety|url=http://searchbusinessanalytics.techtarget.com/feature/NASA-uses-text-analytics-to-bolster-aviation-safety|website=TechTarget Network|access-date=9 May 2017}}</ref> |
|||
=== Machine Learning Model Characteristics === |
|||
[[Predictive maintenance|Predictive]] and [[preventive maintenance]] through data-driven [[machine learning]] is also critical in cost reduction for industrial applications. [[Prognostics]] and health management ([[Prognostics and health management|PHM]]) programs capture the opportunities at the shop floor by modeling equipment health degradation. |
|||
ML models are considered as [[Black box|black-box systems]] given their complexity and intransparency of input-output relation. This reduces the comprehensibility of the system behavior and thus also the acceptance by plant operators. Due to the lack of transparency and the stochasticity of these models, no deterministic proof of functional correctness can be achieved complicating the certification of production equipment. Given their inherent unrestricted prediction behavior, ML models are vulnerable against erroneous or manipulated data further risking the reliability of the production system because of lacking robustness and safety. In addition to high development and deployment costs, the data drifts cause high maintenance costs, which is disadvantageous compared to purely [[Deterministic algorithm|deterministic programs]]. |
|||
== Standard processes for data science in production == |
|||
| ⚫ | |||
The development of ML applications – starting with the identification and selection of the use case and ending with the deployment and maintenance of the application – follows dedicated phases that can be organized in standard process models. The process models assist in structuring the development process and defining requirements that must be met in each phase to enter the next phase. The standard processes can be classified into generic and domain-specific ones. Generic standard processes (e.g., [[Cross-industry standard process for data mining|CRISP-DM]], ASUM-DM, [[Data mining|KDD]], [https://documentation.sas.com/doc/en/emref/14.3/n061bzurmej4j3n1jnj8bbjjm1a2.htm SEMMA], or [https://learn.microsoft.com/en-gb/azure/architecture/data-science-process/overview Team Data Science Process]) describe a generally valid methodology and are thus independent of individual domains.<ref>{{Cite journal |last=Azavedo |first=Ana |date=2008 |title=KDD, SEMMA and CRISP-DM: a parallel overview |journal=IADIS European Conf. Data Mining|s2cid=15309704 }}</ref> Domain-specific processes on the other hand consider specific peculiarities and challenges of special application areas. |
|||
The challenges of industrial AI to unlock the value lies in the transformation of raw data to intelligent predictions for rapid decision-making. In general, there are four major challenges in realizing industrial AI: data, speed, fidelity, and interpretability.<ref name=":0" /> |
|||
The ''Machine Learning Pipeline in Production'' is a domain-specific data science methodology that is inspired by the CRISP-DM model and was specifically designed to be applied in fields of engineering and production technology.<ref>{{Cite book |last1=Krauß |first1=Jonathan |last2=Dorißen |first2=Jonas |last3=Mende |first3=Hendrik |last4=Frye |first4=Maik |last5=Schmitt |first5=Robert H. |title=Production at the leading edge of technology |chapter=Machine Learning and Artificial Intelligence in Production: Application Areas and Publicly Available Data Sets: Maschinelles Lernen und Kü nstliche Intelligenz in der Produktion: Anwendungsgebiete und öffentlich zugängliche Datensätze |date=2019 |editor-last=Wulfsberg |editor-first=Jens Peter |editor2-last=Hintze |editor2-first=Wolfgang |editor3-last=Behrens |editor3-first=Bernd-Arno |chapter-url=https://link.springer.com/chapter/10.1007/978-3-662-60417-5_49 |language=en |location=Berlin, Heidelberg |publisher=Springer |pages=493–501 |doi=10.1007/978-3-662-60417-5_49 |isbn=978-3-662-60417-5|s2cid=213777444 }}</ref> To address the core challenges of ML in engineering – process, data, and model characteristics – the methodology especially focuses on use-case assessment, achieving a common data and process understanding data integration, data preprocessing of real-world production data and the deployment and certification of real-world ML applications. |
|||
[[File:Machine Learning Pipeline in Production.png|center|thumb|645x645px|Machine Learning Pipeline in Production]] |
|||
== Industrial data sources == |
|||
The foundation of most artificial intelligence and machine learning applications in industrial settings are comprehensive datasets from the respective fields. Those datasets act as the basis for training the employed models.<ref name=":2" /> In other domains, like computer vision, speech recognition or language models, extensive reference datasets (e.g. [[ImageNet]], Librispeech,<ref>{{Cite book |url=https://ieeexplore.ieee.org/document/7178964 |access-date=2023-10-18 |date=2015 |language=en-US |doi=10.1109/icassp.2015.7178964 |last1=Panayotov |first1=Vassil |last2=Chen |first2=Guoguo |last3=Povey |first3=Daniel |last4=Khudanpur |first4=Sanjeev |title=2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |chapter=Librispeech: An ASR corpus based on public domain audio books |pages=5206–5210 |isbn=978-1-4673-6997-8 |s2cid=2191379 }}</ref> [[arxiv:2111.09344|The People's Speech]]) and data scraped from the open internet<ref>{{Cite arXiv |last=OpenAI |date=2023 |title=GPT-4 Technical Report |class=cs.CL |eprint=2303.08774 }}</ref> are frequently used for this purpose. Such datasets rarely exist in the industrial context because of high confidentiality requirements <ref name=":3" /> and high specificity of the data. Industrial applications of artificial intelligence are therefore often faced with the problem of data availability.<ref name=":3" /> |
|||
For these reasons, existing open datasets applicable to industrial applications, often originate from public institutions like governmental agencies or universities and data analysis competitions hosted by companies. In addition to this, data sharing platforms exist. However, most of these platforms have no industrial focus and offer limited filtering abilities regarding industrial data sources. |
|||
== Artificial intelligence for business education == |
|||
'''Artificial intelligence for business education''' refers to the academic programs offered by universities that integrate [[artificial intelligence]] (AI) with business management principles. These programs aim to prepare students for the increasing role of AI in business, equipping them with the skills necessary to apply AI technologies to areas such as predictive analytics, supply chain optimization, and decision-making. AI for business education programs are offered at both undergraduate and graduate levels by several universities globally. |
|||
=== Academic Programs === |
|||
Bachelor in Artificial Intelligence for Business (BAIB), Bachelor in Computer Science and Artificial Intelligence (BCSAI), Master of Science in Artificial Intelligence in Business (MS-AIB) – These are new programs that are still in their first cohorts and have yet to prove themselves in the industry. The undergraduate degrees are often offered in conjuction with a BBA as a 5-year double degree program, the undergraduate degrees are going through the acreditation processes in their respective countries. |
|||
Programs that combine AI with business studies vary by institution and degree level. Below are some notable examples: |
|||
'''The Bachelor in Artificial Intelligence for Business (BAIB)''' - This program, started by [[ESADE|Esade]] focuses on the integration of AI and machine learning with core business disciplines such as management, marketing, and finance. The [[ESADE Business School|Esade Business School]] is a highly regarded institution for its business inovation, sustainability focus and future-proof outlook. During the BBA+BAIB, students are trained to apply AI in business environments to improve efficiency, innovation, and decision-making.<ref>{{Cite web |title=AI and Business Degrees - Esade Bachelors |url=https://www.esade.edu/bachelor/en/programmes/double-degree-business-administration-artificial-intelligence-business |access-date=2024-09-11 |website=www.esade.edu |language=en}}</ref> |
|||
'''Bachelor in Computer Science and Artificial Intelligence (BCSAI)''' – Offered along with a BBA by [[IE University]], the BCSAI combines foundational studies in computer science with a specialization in artificial intelligence. The program also provides a strong grounding in business principles, preparing graduates to create AI solutions for business problems and drive technological innovation in the business world.<ref>{{Cite web |title=Bachelor in Computer Science & Artificial Intelligence {{!}} IE University |url=https://www.ie.edu/university/studies/academic-programs/bachelor-computer-science-artificial-intelligence/ |access-date=2024-09-11 |website=University |language=en}}</ref> |
|||
'''Master in Artificial Intelligence for Business (MS-AIB)''' – [[Arizona State University]] (ASU) offers a graduate-level program focused on AI applications in business environments. This degree explores advanced topics such as AI-driven decision-making, big data analysis, and the ethical implications of AI in business. The program is designed for professionals seeking to leverage AI technologies to transform business practices and improve efficiency. |
|||
Engineering systems now generate a lot of data and modern industry is indeed a [[big data]] environment. However, industrial data usually is structured, but may be low-quality.<ref name=":0" /> |
|||
=== Curriculum Structure === |
|||
Production process happens fast and the equipment and work piece can be expensive, the AI applications need to be applied in real-time to be able to detect anomalies immediately to avoid waste and other consequences. Cloud-based solutions can be powerful and fast, but they still would not fit certain computation efficiency requirements. Edge computing may be a better choice in such scenario.<ref name=":0" /> |
|||
These programs typically include a combination of AI and business courses. Core subjects often cover topics such as machine learning, data science, business strategy, and financial management. The programs aim to give students a broad understanding of AI applications within a business environment, while also allowing them to specialize in areas such as supply chain management, marketing analytics, and AI-driven innovation. |
|||
In addition to technical courses, many programs include practical training, such as internships, real-world AI projects, and industry case studies. This helps students gain practical experience in applying AI tools and techniques to solve business challenges. |
|||
Unlike consumer-faced AI recommendations systems which have a high tolerance for false positives and negatives, even a very low rate of false positives or negatives rate may cost the total credibility of AI systems. Industrial AI applications are usually dealing with critical issues related to safety, reliability, and operations. Any failure in predictions could incur a negative economic and/or safety impact on the users and discourage them to rely on AI systems.<ref name=":0" /> |
|||
=== Accreditation === |
|||
Besides prediction accuracy and performance fidelity, the industrial AI systems must also go beyond prediction results and give root cause analysis for anomalies. This requires that during development, data scientists need to work with domain experts and include [[domain know-how]] into the modeling process, and have the model adaptively learn and accumulate such insights as knowledge.<ref name=":0" /> |
|||
Many universities offering these degrees hold accreditation from recognized educational bodies, ensuring that their programs meet rigorous academic and industry standards. For example, [[ESADE]] and [[IE University]] are both accredited by institutions such as EQUIS and AACSB, which evaluate the quality of business education programs. Similarly, [[Arizona State University]] holds accreditation for its graduate programs in business and technology. |
|||
==See also== |
==See also== |
||
| Line 44: | Line 75: | ||
{{Reflist}} |
{{Reflist}} |
||
[[Category: |
[[Category:Applications of artificial intelligence]] |
||
Latest revision as of 00:30, 17 December 2024
| Part of a series on |
| Artificial intelligence |
|---|
_artificial_intelligence_icon.png){kind=icon} |
Industrial artificial intelligence, or industrial AI, usually refers to the application of artificial intelligence to industry and business. Unlike general artificial intelligence which is a frontier research discipline to build computerized systems that perform tasks requiring human intelligence, industrial AI is more concerned with the application of such technologies to address industrial pain-points for customer value creation, productivity improvement, cost reduction, site optimization, predictive analysis[1] and insight discovery.[2]
Artificial intelligence and machine learning have become key enablers to leverage data in production in recent years due to a number of different factors: More affordable sensors and the automated process of data acquisition; More powerful computation capability of computers to perform more complex tasks at a faster speed with lower cost; Faster connectivity infrastructure and more accessible cloud services for data management and computing power outsourcing.[3]
Categories
[edit]Possible applications of industrial AI and machine learning in the production domain can be divided into seven application areas:[4]
- Market & Trend Analysis
- Machinery & Equipment
- Intralogistics
- Production Process
- Supply Chain
- Building
- Product
Each application area can be further divided into specific application scenarios that describe concrete AI/ML scenarios in production. While some application areas have a direct connection to production processes, others cover production adjacent fields like logistics or the factory building.[4]
An example from the application scenario Process Design & Innovation are collaborative robots. Collaborative robotic arms are able to learn the motion and path demonstrated by human operators and perform the same task.[5] Predictive and preventive maintenance through data-driven machine learning are exemplary application scenarios from the Machinery & Equipment application area.[4]
Challenges
[edit]In contrast to entirely virtual systems, in which ML applications are already widespread today, real-world production processes are characterized by the interaction between the virtual and the physical world. Data is recorded using sensors and processed on computational entities and, if desired, actions and decisions are translated back into the physical world via actuators or by human operators.[6] This poses major challenges for the application of ML in production engineering systems. These challenges are attributable to the encounter of process, data and model characteristics: The production domain's high reliability requirements, high risk and loss potential, the multitude of heterogeneous data sources and the non-transparency of ML model functionality impede a faster adoption of ML in real-world production processes.
In particular, production data comprises a variety of different modalities, semantics and quality.[7] Furthermore, production systems are dynamic, uncertain and complex,[7] and engineering and manufacturing problems are data-rich but information-sparse.[8] Besides that, due the variety of use cases and data characteristics, problem-specific data sets are required, which are difficult to acquire, hindering both practitioners and academic researchers in this domain.[9]
Process and Industry Characteristics
[edit]The domain of production engineering can be considered as a rather conservative industry when it comes to the adoption of advanced technology and their integration into existing processes. This is due to high demands on reliability of the production systems resulting from the potentially high economic harm of reduced process effectiveness due to e.g., additional unplanned downtime or insufficient product qualities. In addition, the specifics of machining equipment and products prevent area-wide adoptions across a variety of processes. Besides the technical reasons, the reluctant adoption of ML is fueled by a lack of IT and data science expertise across the domain.[4]
Data Characteristics
[edit]The data collected in production processes mainly stem from frequently sampling sensors to estimate the state of a product, a process, or the environment in the real world. Sensor readings are susceptible to noise and represent only an estimate of the reality under uncertainty. Production data typically comprises multiple distributed data sources resulting in various data modalities (e.g., images from visual quality control systems, time-series sensor readings, or cross-sectional job and product information). The inconsistencies in data acquisition lead to low signal-to-noise ratios, low data quality and great effort in data integration, cleaning and management. In addition, as a result from mechanical and chemical wear of production equipment, process data is subject to various forms of data drifts.
Machine Learning Model Characteristics
[edit]ML models are considered as black-box systems given their complexity and intransparency of input-output relation. This reduces the comprehensibility of the system behavior and thus also the acceptance by plant operators. Due to the lack of transparency and the stochasticity of these models, no deterministic proof of functional correctness can be achieved complicating the certification of production equipment. Given their inherent unrestricted prediction behavior, ML models are vulnerable against erroneous or manipulated data further risking the reliability of the production system because of lacking robustness and safety. In addition to high development and deployment costs, the data drifts cause high maintenance costs, which is disadvantageous compared to purely deterministic programs.
Standard processes for data science in production
[edit]The development of ML applications – starting with the identification and selection of the use case and ending with the deployment and maintenance of the application – follows dedicated phases that can be organized in standard process models. The process models assist in structuring the development process and defining requirements that must be met in each phase to enter the next phase. The standard processes can be classified into generic and domain-specific ones. Generic standard processes (e.g., CRISP-DM, ASUM-DM, KDD, SEMMA, or Team Data Science Process) describe a generally valid methodology and are thus independent of individual domains.[10] Domain-specific processes on the other hand consider specific peculiarities and challenges of special application areas.
The Machine Learning Pipeline in Production is a domain-specific data science methodology that is inspired by the CRISP-DM model and was specifically designed to be applied in fields of engineering and production technology.[11] To address the core challenges of ML in engineering – process, data, and model characteristics – the methodology especially focuses on use-case assessment, achieving a common data and process understanding data integration, data preprocessing of real-world production data and the deployment and certification of real-world ML applications.
Industrial data sources
[edit]The foundation of most artificial intelligence and machine learning applications in industrial settings are comprehensive datasets from the respective fields. Those datasets act as the basis for training the employed models.[7] In other domains, like computer vision, speech recognition or language models, extensive reference datasets (e.g. ImageNet, Librispeech,[12] The People's Speech) and data scraped from the open internet[13] are frequently used for this purpose. Such datasets rarely exist in the industrial context because of high confidentiality requirements [9] and high specificity of the data. Industrial applications of artificial intelligence are therefore often faced with the problem of data availability.[9]
For these reasons, existing open datasets applicable to industrial applications, often originate from public institutions like governmental agencies or universities and data analysis competitions hosted by companies. In addition to this, data sharing platforms exist. However, most of these platforms have no industrial focus and offer limited filtering abilities regarding industrial data sources.
Artificial intelligence for business education
[edit]Artificial intelligence for business education refers to the academic programs offered by universities that integrate artificial intelligence (AI) with business management principles. These programs aim to prepare students for the increasing role of AI in business, equipping them with the skills necessary to apply AI technologies to areas such as predictive analytics, supply chain optimization, and decision-making. AI for business education programs are offered at both undergraduate and graduate levels by several universities globally.
Academic Programs
[edit]Bachelor in Artificial Intelligence for Business (BAIB), Bachelor in Computer Science and Artificial Intelligence (BCSAI), Master of Science in Artificial Intelligence in Business (MS-AIB) – These are new programs that are still in their first cohorts and have yet to prove themselves in the industry. The undergraduate degrees are often offered in conjuction with a BBA as a 5-year double degree program, the undergraduate degrees are going through the acreditation processes in their respective countries.
Programs that combine AI with business studies vary by institution and degree level. Below are some notable examples:
The Bachelor in Artificial Intelligence for Business (BAIB) - This program, started by Esade focuses on the integration of AI and machine learning with core business disciplines such as management, marketing, and finance. The Esade Business School is a highly regarded institution for its business inovation, sustainability focus and future-proof outlook. During the BBA+BAIB, students are trained to apply AI in business environments to improve efficiency, innovation, and decision-making.[14]
Bachelor in Computer Science and Artificial Intelligence (BCSAI) – Offered along with a BBA by IE University, the BCSAI combines foundational studies in computer science with a specialization in artificial intelligence. The program also provides a strong grounding in business principles, preparing graduates to create AI solutions for business problems and drive technological innovation in the business world.[15]
Master in Artificial Intelligence for Business (MS-AIB) – Arizona State University (ASU) offers a graduate-level program focused on AI applications in business environments. This degree explores advanced topics such as AI-driven decision-making, big data analysis, and the ethical implications of AI in business. The program is designed for professionals seeking to leverage AI technologies to transform business practices and improve efficiency.
Curriculum Structure
[edit]These programs typically include a combination of AI and business courses. Core subjects often cover topics such as machine learning, data science, business strategy, and financial management. The programs aim to give students a broad understanding of AI applications within a business environment, while also allowing them to specialize in areas such as supply chain management, marketing analytics, and AI-driven innovation.
In addition to technical courses, many programs include practical training, such as internships, real-world AI projects, and industry case studies. This helps students gain practical experience in applying AI tools and techniques to solve business challenges.
Accreditation
[edit]Many universities offering these degrees hold accreditation from recognized educational bodies, ensuring that their programs meet rigorous academic and industry standards. For example, ESADE and IE University are both accredited by institutions such as EQUIS and AACSB, which evaluate the quality of business education programs. Similarly, Arizona State University holds accreditation for its graduate programs in business and technology.
See also
[edit]References
[edit]- ^ "Reducing downtime using AI in Oil and Gas". Tech27.
- ^ Sallomi, Paul. "Artificial Intelligence Goes Mainstream". WSJ. The Wall Street Journal - CIO Journal - Deloitte. Retrieved 9 May 2017.
- ^ Schatsky, David; Muraskin, Craig; Gurumurthy, Ragu. "Cognitive technologies: The real opportunities for business". Deloitte Review.
- ^ a b c d Krauß, J.; Hülsmann, T.; Leyendecker, L.; Schmitt, R. H. (2023). "Application Areas, Use Cases, and Data Sets for Machine Learning and Artificial Intelligence in Production". In Liewald, Mathias; Verl, Alexander; Bauernhansl, Thomas; Möhring, Hans-Christian (eds.). Production at the Leading Edge of Technology. Lecture Notes in Production Engineering. Cham: Springer International Publishing. pp. 504–513. doi:10.1007/978-3-031-18318-8_51. ISBN 978-3-031-18318-8.
- ^ "What Does Collaborative Robot Mean ?". Retrieved 9 May 2017.
- ^ Monostori, L.; Kádár, B.; Bauernhansl, T.; Kondoh, S.; Kumara, S.; Reinhart, G.; Sauer, O.; Schuh, G.; Sihn, W.; Ueda, K. (2016-01-01). "Cyber-physical systems in manufacturing". CIRP Annals. 65 (2): 621–641. doi:10.1016/j.cirp.2016.06.005. ISSN 0007-8506.
- ^ a b c Wuest, Thorsten; Weimer, Daniel; Irgens, Christopher; Thoben, Klaus-Dieter (January 2016). "Machine learning in manufacturing: advantages, challenges, and applications". Production & Manufacturing Research. 4 (1): 23–45. doi:10.1080/21693277.2016.1192517. ISSN 2169-3277. S2CID 52037185.
- ^ Lu, Stephen C-Y. (1990-01-01). "Machine learning approaches to knowledge synthesis and integration tasks for advanced engineering automation". Computers in Industry. 15 (1): 105–120. doi:10.1016/0166-3615(90)90088-7. ISSN 0166-3615.
- ^ a b c Jourdan, Nicolas; Longard, Lukas; Biegel, Tobias; Metternich, Joachim (2021). "Machine Learning For Intelligent Maintenance And Quality Control: A Review Of Existing Datasets And Corresponding Use Cases". doi:10.15488/11280.
{{cite journal}}: Cite journal requires|journal=(help) - ^ Azavedo, Ana (2008). "KDD, SEMMA and CRISP-DM: a parallel overview". IADIS European Conf. Data Mining. S2CID 15309704.
- ^ Krauß, Jonathan; Dorißen, Jonas; Mende, Hendrik; Frye, Maik; Schmitt, Robert H. (2019). "Machine Learning and Artificial Intelligence in Production: Application Areas and Publicly Available Data Sets: Maschinelles Lernen und Kü nstliche Intelligenz in der Produktion: Anwendungsgebiete und öffentlich zugängliche Datensätze". In Wulfsberg, Jens Peter; Hintze, Wolfgang; Behrens, Bernd-Arno (eds.). Production at the leading edge of technology. Berlin, Heidelberg: Springer. pp. 493–501. doi:10.1007/978-3-662-60417-5_49. ISBN 978-3-662-60417-5. S2CID 213777444.
- ^ Panayotov, Vassil; Chen, Guoguo; Povey, Daniel; Khudanpur, Sanjeev (2015). "Librispeech: An ASR corpus based on public domain audio books". 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 5206–5210. doi:10.1109/icassp.2015.7178964. ISBN 978-1-4673-6997-8. S2CID 2191379. Retrieved 2023-10-18.
- ^ OpenAI (2023). "GPT-4 Technical Report". arXiv:2303.08774 [cs.CL].
- ^ "AI and Business Degrees - Esade Bachelors". www.esade.edu. Retrieved 2024-09-11.
- ^ "Bachelor in Computer Science & Artificial Intelligence | IE University". University. Retrieved 2024-09-11.