Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2023 Feb 22;14(3):508.
doi: 10.3390/mi14030508.

Review of Intelligence for Additive and Subtractive Manufacturing: Current Status and Future Prospects

Affiliations
Review

Review of Intelligence for Additive and Subtractive Manufacturing: Current Status and Future Prospects

M Azizur Rahman et al. Micromachines (Basel). .

Abstract

Additive manufacturing (AM), an enabler of Industry 4.0, recently opened limitless possibilities in various sectors covering personal, industrial, medical, aviation and even extra-terrestrial applications. Although significant research thrust is prevalent on this topic, a detailed review covering the impact, status, and prospects of artificial intelligence (AI) in the manufacturing sector has been ignored in the literature. Therefore, this review provides comprehensive information on smart mechanisms and systems emphasizing additive, subtractive and/or hybrid manufacturing processes in a collaborative, predictive, decisive, and intelligent environment. Relevant electronic databases were searched, and 248 articles were selected for qualitative synthesis. Our review suggests that significant improvements are required in connectivity, data sensing, and collection to enhance both subtractive and additive technologies, though the pervasive use of AI by machines and software helps to automate processes. An intelligent system is highly recommended in both conventional and non-conventional subtractive manufacturing (SM) methods to monitor and inspect the workpiece conditions for defect detection and to control the machining strategies in response to instantaneous output. Similarly, AM product quality can be improved through the online monitoring of melt pool and defect formation using suitable sensing devices followed by process control using machine learning (ML) algorithms. Challenges in implementing intelligent additive and subtractive manufacturing systems are also discussed in the article. The challenges comprise difficulty in self-optimizing CNC systems considering real-time material property and tool condition, defect detections by in-situ AM process monitoring, issues of overfitting and underfitting data in ML models and expensive and complicated set-ups in hybrid manufacturing processes.

Keywords: data analytics; digital twin; feedback control; intelligent manufacturing; smart system.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Interplay between computer science, information communication technology (ICT) and manufacturing (reprinted with permission from [2]. Copyright 2016 CIRP).
Figure 2
Figure 2
Numeric flow diagram for PRISMA regarding the literature review.
Figure 3
Figure 3
Visual representation of the article’s percentage according to the search engine (upper left), manufacturing process related proportion (upper right), and article’s year growth (lower portion).
Figure 4
Figure 4
Schematic representation of the basic architecture of a smart system.
Figure 5
Figure 5
Visual schematic diagram of (a) the experimental setup (reprinted with permission from [89]. Copyright 2020 The Society of Manufacturing Engineers). (b) Framework for tool wear prediction (reprinted with permission from [91]. Copyright 2020 Elsevier B.V.).
Figure 6
Figure 6
(a) Various depth-of-cuts in machining a freeform surface (reprinted with permission from [93]. Copyright 2015 Springer Nature). (b) Dynamic feature information and its applications (reprinted with permission from [94]. Copyright 2015 IOS Press). (c) Three parts of an intelligent milling system, including data collection, information modelling and process optimization (reprinted with permission from [95]. Copyright 2022 Elsevier B.V.).
Figure 7
Figure 7
In-process measurement, repair, and evaluation method of defective microstructures on a roll mold illustrated as (a) the real-time detection of the defect positions; (b) characterization of the defect surface profiles; (c) repairing the defective microstructure elements; and (d) evaluating the repair results (reprinted with permission from [97]. Copyright 2014 Elsevier B.V.).
Figure 8
Figure 8
(a) integrated ANN–GA approach for process optimization (reprinted with permission from [101]. Copyright 2010 Elsevier B.V.); (b) intelligent system framework of debris removal operations [105]; (c) machine earning (ML) and predictive modelling for WEDM process (reprinted with permission from [107]. Copyright 2018 Elsevier B.V.).
Figure 9
Figure 9
Illustration of the (a) concept of transfer learning; (b) domains, tasks and features of chatter detection (reprinted with permission from [112]. Copyright 2022 Elsevier B.V.). (c) Surface roughness prediction framework for the assembly interface: (i) pre-training of the surface roughness prediction model in the source domain; (ii) transfer learning for the modules of the source domain model; (iii) prediction of surface roughness in the target domain; and (iv) surface roughness [113].
Figure 10
Figure 10
Defects in AM parts by selective laser sintering processes.
Figure 11
Figure 11
Defects in the proposed framework for the control strategies [144].
Figure 12
Figure 12
(a) General configuration of a machine learning system (reprinted with permission from [147]. Copyright 2004 Elsevier B.V.). (b) Taxonomy and applications of ML in AM as proposed (reprinted with permission from [148]. Copyright 2020 The Minerals, Metals & Materials Society).
Figure 13
Figure 13
(a) Powder bed fusion (PBF) process monitoring and control framework (reprinted with permission from [151]. Copyright 2022 Springer Nature). (b) Multiple data sensors and feature detection for a wide range of signal monitoring, feedback, and control (reprinted with permission from [152]. Copyright 2020 Elsevier B.V.).
Figure 14
Figure 14
Various post-processing techniques utilized for metal AM (reprinted with permission from [156]. Copyright 2022 Springer Nature).
Figure 15
Figure 15
(a) Strategy for predicting surface roughness using the SVM classification algorithm (reprinted with permission from [162]. Copyright 2016 Elsevier B.V.); (b) Combined NNW and GA strategy for polishing uneven surfaces (reprinted with permission from [163]. Copyright 2017 Springer Nature).
Figure 16
Figure 16
(a) Surface roughness prediction model framework. (b) MJP setup. (c) SEM images before and after MJP (reprinted with permission from [164]. Copyright 2022 Elsevier B.V.).
Figure 17
Figure 17
(a) Traditional post-processing and hybrid manufacturing approach (reprinted with permission from [36]. Copyright 2020 Springer Nature). (b) Different process combinations in hybrid machines [69].
Figure 18
Figure 18
Schematic of hybrid additive and subtractive processes (Reprinted with permission from Ref. [26]. Copyright 2016 Elsevier B.V.).
Figure 19
Figure 19
(a) Description of RECLAIM remanufacturing (reprinted with permission from [171]. Copyright 2015 Elsevier B.V.); (b) flow chart of the operation sequencing algorithm of the HM process [182]; (c) framework for the design of process planning (reprinted with permission from [183]. Copyright 2018 Elsevier B.V.).
Figure 20
Figure 20
(a) Data streams in HM. (b) Spinning the digital thread with HM (reprinted with permission from [185]. Copyright 2021 Society of Manufacturing Engineers (SME)).
Figure 21
Figure 21
(a) Generalized AM techniques (reprinted with permission from [188]. Copyright 2021 Elsevier B.V.); (b) schematic of a typical high-pressure CSAM (reprinted with permission from [189]. Copyright 2021 Chinese Society of Aeronautics and Astronautics); (c) schematic diagram for coating development during CSAM (reprinted with permission from [188]. Copyright 2021 Elsevier B.V.); (d) pure Al on Al6061 (as sprayed); and (e) pure Al on Al6061 (after machining); (f) hybrid robotic cell (reprinted with permission from [190]. Copyright 2012–2023 Polycontrols Inc).
Figure 22
Figure 22
Microhardness variation of stainless steel 316L in different additive/subtractive/hybrid techniques.
Figure 23
Figure 23
Analysis of the use of intelligence in different manufacturing technologies based on the literature survey.
Figure 24
Figure 24
(a) Generalized traditional open-loop configuration of CAM and CNC systems with external data acquisition (reprinted with permission from [213] Copyright 2017 ASTM International). (b) Influence of process data monitoring with ML and real-time control in closed loop feedback [123].
Figure 25
Figure 25
ML algorithms, sensing principles and detected defects in AM.
Figure 26
Figure 26
Essential features of intelligent HM post processing.
Figure 27
Figure 27
(a) Intelligent sensor-based machining condition sensing; (b) schematic of AI-enabled dynamic process parameter optimization framework considering progressive tool-wear (reprinted with permission from [232]. Copyright 2021 Society of Manufacturing Engineers (SME)).
Figure 28
Figure 28
Four-dimensional printing material demonstration (a) of the transition between the gripper shape with programming and heating environment [235]; (b) thermo-responsive and time-lapsed images of a gripper grabbing an object [235]; and (c) possible uses of AI in 3D- and 4D printing applications [237].
Figure 29
Figure 29
Schematic representation of (a) the evolution of connectivity in manufacturing (reprinted with permission from [241]. Copyright 2019 Elsevier B.V.); (b) M2M and IoT communication in manufacturing process.
Figure 30
Figure 30
(a) Conceptual framework for a CPMT powered cloud manufacturing environment (reprinted with permission from [5]. Copyright 2019 Elsevier B.V.). (b) DT process in a real-time diagnostic control capacity (reprinted with permission from [257]. Copyright 2021 Elsevier B.V.).
Figure 31
Figure 31
(a) framework of the integrated manufacturing monitoring (reprinted with permission from [78]. Copyright 2020 Elsevier B.V.); (b) hierarchy of the AM digital twin (reprinted with permission from [267]. Copyright 2022 Elsevier B.V.).

References

    1. Arinez J.F., Chang Q., Gao R.X., Xu C., Zhang J. Artificial Intelligence in Advanced Manufacturing: Current Status and Future Outlook. J. Manuf. Sci. Eng. 2020;142:110804. doi: 10.1115/1.4047855. - DOI
    1. Monostori L., Kádár B., Bauernhansl T., Kondoh S., Kumara S., Reinhart G., Sauer O., Schuh G., Sihn W., Ueda K. Cyber-Physical Systems in Manufacturing. CIRP Ann. 2016;65:621–641. doi: 10.1016/j.cirp.2016.06.005. - DOI
    1. Lim M.K., Xiong W., Lei Z. Theory, Supporting Technology and Application Analysis of Cloud Manufacturing: A Systematic and Comprehensive Literature Review. Ind. Manag. Data Syst. 2020;120:1585–1614. doi: 10.1108/IMDS-10-2019-0570. - DOI
    1. Volpe G., Mangini A.M., Fanti M.P. An Architecture for Digital Processes in Manufacturing with Blockchain, Docker and Cloud Storage; Proceedings of the 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE); Lyon, France. 23–27 August 2021; pp. 39–44. - DOI
    1. Liu C., Vengayil H., Lu Y., Xu X. A Cyber-Physical Machine Tools Platform Using OPC UA and MTConnect. J. Manuf. Syst. 2019;51:61–74. doi: 10.1016/j.jmsy.2019.04.006. - DOI

LinkOut - more resources