Machine Learning and Artificial Intelligence in CNC Machine Tools, A Review

Abstract

Artificial Intelligence (AI) and Machine learning (ML) represents an important evolution in computer science and data processing systems which can be used in order to enhance almost every technology-enabled service, products, and industrial applications. A subfield of artificial intelligence and computer science is named machine learning which focuses on using data and algorithms to simulate learning process of machines and enhance the accuracy of the systems. Machine learning systems can be applied to the cutting forces and cutting tool wear prediction in CNC machine tools in order to increase cutting tool life during machining operations. Optimized machining parameters of CNC machining operations can be obtained by using the advanced machine learning systems in order to increase efficiency during part manufacturing processes. Moreover, surface quality of machined components can be predicted and improved using advanced machine learning systems to improve the quality of machined parts. In order to analyze and minimize power usage during CNC machining operations, machine learning is applied to prediction techniques of energy consumption of CNC machine tools. In this paper, applications of machine learning and artificial intelligence systems in CNC machine tools is reviewed and future research works are also recommended to present an overview of current research on machine learning and artificial intelligence approaches in CNC machining processes. As a result, the research filed can be moved forward by reviewing and analysing recent achievements in published papers to offer innovative concepts and approaches in applications of artificial Intelligence and machine learning in CNC machine tools.

Full text

Journal Pre-proof
Machine Learning and Artificial Intelligence in CNC Machine Tools, A
Review
Mohsen Soori , Behrooz Arezoo , Roza Dastres
PII: S2667-3444(23)00001-4
DOI: https://doi.org/10.1016/j.smse.2023.100009
Reference: SMSE 100009
To appear in: Sustainable Manufacturing and Service Economics
Received date: 11 October 2022
Revised date: 17 December 2022
Accepted date: 13 January 2023
Please cite this article as: Mohsen Soori , Behrooz Arezoo , Roza Dastres , Machine Learning and
Artificial Intelligence in CNC Machine Tools, A Review, Sustainable Manufacturing and Service Eco-
nomics (2023), doi: https://doi.org/10.1016/j.smse.2023.100009
This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition
of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of
record. This version will undergo additional copyediting, typesetting and review before it is published
in its final form, but we are providing this version to give early visibility of the article. Please note that,
during the production process, errors may be discovered which could affect the content, and all legal
disclaimers that apply to the journal pertain.
©2023 Published by Elsevier B.V.
This is an open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/)

Machine Learning and Artificial Intelligence in CNC Machine Tools, A
Review
Mohsen Soori 1*, Behrooz Arezoo 2, Roza Dastres 3
1 Department of Aeronautical Engineering, University of Kyrenia, Kyrenia, North Cyprus, Via Mersin 10, Turkey
2 CAD/CAPP/CAM Research Center, Department of Mechanical Engineering, Amirkabir University of Technology
(Tehran Polytechnic), 424 Hafez Avenue, Tehran 15875-4413, Iran
3 Department of Computer Engineering, Near East University, Lefkosha, North Cyprus, Via Mersin 10, Turkey
* Corresponding Author
E-Mails: Mohsen.soori@gmail.com, Mohsen.soori@kyrenia.edu.tr (Mohsen Soori), barezoo@yahoo.com,
arezoo@aut.ac.ir (Behrooz Arezoo), roza.dastres@yahoo.com (Roza Dastres)
Abstract:
Artificial Intelligence (AI) and Machine learning (ML) represents an important evolution in computer science and
data processing systems which can be used in order to enhance almost every technology-enabled service,
products, and industrial applications. A subfield of artificial intelligence and computer science are named machine
learning which focuses on using data and algorithms to simulate learning process of machin es and enhance the
accuracy of the systems. Machine learning systems can be applied to the cutting forces and cutting tool wear
prediction in CNC machine tools in order to increase cutting tool life during machining operations. Optimized
machining parameters of CNC machining operations can be obtained by using the advanced machine learning
systems in order to increase efficiency during part manufacturing processes. Moreover, surface quality of
machined components can be predicted and improved using advanced machine learning systems to improve the
quality of machined parts. In order to analyze and minimize power usage during CNC machining operations,
machine learning is applied to prediction techniques of energy consumption of CNC machine tools. In this paper,
applications of machine learning and artificial intelligence systems in CNC machine tools is reviewed and future
research works are also recommended to present an overview of current research on machine learning and
artificial intelligence approaches in CNC machining processes. As a result, the research filed can be moved forward
by reviewing and analysing recent achievements in published papers to offer innovative concepts and approaches
in applications of artificial Intelligence and machine learning in CNC machine tools.
Keywords: Machine learning, Artificial intelligence, CNC machine tools
1- Introduction
CNC machining operation is one of the most important part-production methodologies, and it is often referred to
as the engine of modern manufacturing processes. The automotive and medical sectors, aerospace, gas and oil,
and warehousing services, are using the CNC machining operations to create parts in different applications [1].
CNC machining is generally used in manufacture of every machine, molded part, or finished product as one of the
most important manufacturing processes. CNC machinery has paved the way in manufacturing and machining,

allowing businesses to achieve their goals and targets in a variety of ways. However, because manufacturing
methodologies is always evolving and new technologies are being introduced, it is critical to consider future of CNC
machining operations [2, 3]. Machine learning (ML) is the study of computer algorithms that gives computers the
capacity to automatically learn from data and prior experiences in order to find patterns and make predictions
without human involvement. The ML and applications in different areas of study are considered to be a
component of artificial intelligence [4-6].
Machine learning and artificial intelligence in particular raise plenty of concerns about the future of CNC machining
operations and how these concepts will evolve future works of manufacturing companies [7]. The way a machine
learns, adapts, and optimizes output can also be influenced by real-time data, analytics, and deep learning. Data
sets are essential for operators to understand how a machine works and, eventually, how a whole floor of
machines works together [8, 9]. Due to the development of affordable, reliable, and resilient sensors and
acquisition and communication systems, novel implementations of machine learning approaches for tool condition
monitoring can be presented [10]. Machine learning systems are capable of completely examine data and identify
various types of areas which should be modified. Machine tools are increasingly being equipped with edge
computing options to record internal drive signals at high frequency in order to supply the necessary vast quantity
of data for the use of machine learning techniques in manufacturing [11]. Productivity and efficiency are two areas
where artificial intelligence can modify CNC machine tools operations in order to enhance accuracy of CNC
machining operations[12]. Machines can generate and analyze production data and provide real-time findings to
human operators are effective devices for increasing productivity in part production processes. As a result, shop
owners can quickly adjust the way a machine operates using the modified data generated by advanced machine
learning algorithms in order to enhance productivity of part manufacturing [13]. Having more knowledge and
making better decisions in process planning strategies means less downtime on the work floor during process of
part production. Production and maintenance process of part manufacturing using CNC machine tools can be
developed using the machine learning and the artificial intelligence in order to enhance efficiency in part
manufacturing operations [14].
The CNC machining operations must be optimized in order to save money and time and increase overall profit per
production period [15]. Artificial intelligence can forecast periods of servicing and equipment of CNC machine tools
structures by linking to production data such as machine performance and tool life. Data from AI will also indicate
how long a machine can operate before it requires maintenance. So, the predictive data of the AI implies fewer
tool failures, longer tool life, reduced downtime, and machining time which can lead to money savings in part
production [16, 17].
Applications of deep learning in CNC machining and monitoring systems is reviewed in order to develop the
monitoring systems of machining operations using the deep learning and neural network systems [18]. In order to
detect defects in manufacturing operations, applications of deep learning systems in part production is reviewed
[19]. A review on machine and deep learning methods applied to industrial challenges is presented in order to
develop the operation management during process of part production [20]. Applications of machine learning
systems in sustainable manufacturing is reviewed to modify models of big data analysis in process planning of part
production [21]. Deep learning for smart manufacturing is reviewed in order to improve performances of part
production process [22]. A review in smart manufacturing systems using the machine learning is presented in order
to present future directions in the process of part production [23].
Soori et al. [24-27] provided improvement of CNC machining in digital settings using virtual machining methods
and processes. Soori et al. [28] provided a review of current developments in friction stir welding operations in
order to examine and improve efficiency in the process of component manufacturing employing welding
techniques. Soori and Asamel [29] investigated applications of simulated milling systems to reduce residual stress
and deflection error throughout five-axis end milling of turbine blades. Soori and Asmael [30] created applications
of virtual machining system in order to assess and reduce the cutting temperature during machining processes of
components. Soori et al. [31] proposed an improved virtual machining method to improve surface properties
throughout milling operations of turbine blades. To decrease displacement error during five-axis milling
procedures of impeller blades, Soori and Asmael [32] invented virtual milling approaches. Soori and Arezoo [33]

presented a review in residual stress to assess and decrease residual stress during machining processes. To
minimize surface integrity and residual stress during grinding operations of Inconel 718, optimized machining
parameters using the Taguchi optimization approach is presented by Soori and Arezoo [34]. To increase cutting
tool life during machining operations, different methods of tool wear prediction is studied by Soori and Arezoo
[35]. Computer aided process planning is reviewed by Soori and Asmael [36] in order to enhance productivity in
process of part manufacturing. Soori and Asmael [37] provided a summary of existing developments from
published articles in order to examine and improve the parameter optimization technique of machining processes.
Dastres et al.[38] conducted research on RFID-based wireless manufacturing systems to increase energy efficiency,
data quality and availability throughout the supply chain, and accuracy and reliability during the components
manufacturing process.
Developments in web-based decision support systems is presented by Dastres and Soori [39] in order to build
decision support systems for data warehouse operations. Dastres and Soori [40] presented a review of current
research and uses of artificial neural networks in a variety of disciplines, including risk analysis systems, drone
control, welding quality analysis, and computer quality analysis to develop the application of artificial neural
networks in performance enhancement of engineering products. In order to decrease the effects of technology
development to the natural disaster, Dastres and Soori [41] discussed the use of information and communication
technology in environmental conservation. To enhance security in the networks and web of data, secure socket
layer is presented by Dastres and Soori [42]. Advances in web-based decision support system is reviewed by
Dastres and Soori [43] in order to develop the methodology of decision support systems by analyzing and
suggesting the gaps between presented techniques. To enhance security measure in networks, a review in recent
development of network threats is presented by Dastres and Soori [44]. Advanced image processing systems is
reviewed by Dastres and Soori [45] to develop the capabilities of image processing systems in different
applications.
Applications of machine learning and artificial intelligence systems in CNC machine tools are investigated in the
research work by reviewing and analyzing recent achievements from published papers. The research works are
organized into categories based on the applications of MA and AI in CNC machine tools, and future research work
directions in the field are also recommended. As a result, new ideas are presented by studying and analyzing
recent achievements from published papers in order to enhance productivity and added value in component
manufacturing processes employing CNC machining operations.
2- Methodology of review in data extraction
Different applications of ML and AI in CNC machining operations regarding to the effects of the algorithms to
output of CNC machining operations is reviewed in the study. Reducing machine downtime, optimization of CNC
machine tools, cutting tool wear prediction, cutting force model, CNC machine tool maintenance, monitoring of
machining operations, surface quality prediction and energy prediction systems are considered in order to review
the applications of ML and AI in CNC machining operations. The challenges as well as advantages of methods in
terms of productivity enhancement of CNC machining operations using ML and AI are reviewed in order to present
the gap between the published research works. Finally, future directions of research work are suggested in order
to develop the applications of ML and AI in productivity enhancement of CNC machining operations.
3- Reducing machine tool downtime
Equipment failures are a constant occurrence in shipping and industrial sectors. Unanticipated equipment failures
or vehicle breakdowns can have detrimental effects on production schedules, transportation planning, and
capacity management throughout the production process [46, 47]. Recent improvements and trends in predictive
maintenance using the data-driven approaches is presented in order to improve safety, reliability and enabling
predictive maintenance decision-making in different industrial applications [48]. Workflow of predictive
maintenance is shown in the figure 1 [48].

Fig. 1. Workflow of predictive maintenance [48].
Bad maintenance, machine tool part failure, numerous shift changes, and other factors can cause downtime in
machining processes. The machining downtime should be minimized in order to increase efficiency in part
production processes [49]. Standard components on CNC drills, lathes, and mills can be monitored by the sensors,
in order to predict failure and life cycles of machine tool parts. The life time of cutting tool is an important factor of
advanced machining operations due to the tool wear in order to decrease downtime in process of part production
[50]. Sensor-assisted planned downtime allows for precisely the proper amount of maintenance and increases the
working life of CNC machine tool components [51]. Machine learning and artificial intelligence (AI) can interpret
the data and assist manufacturers in determining the optimal time to schedule downtime. Hundreds of different
manufacturing businesses and thousands of various equipment provide streaming data of raw materials to the
company [52]. When a machine tool is not working due to some reasons, maintenance of machine tool can be
implemented. As a consequence, efficient maintenance period regarding the reduction of machine downtime can
be obtained using the applications of ML and AI in CNC machining operations in order to save money, time, and
resources during the manufacturing process using CNC machine tools.
4- Optimization of CNC Machine Tools
Optimization of machining operations are recently considered as a crucial aspect of machine learning in different
research works. Optimization approaches using machine learning are more studied when the amount of data
grows exponentially and model complexity rises [53]. Incremental optimization is at the heart of future
manufacturing, from the supply chain to the completed items. The optimization of CNC machine tool operations is
crucial for saving money and eventually increasing overall profit per production run, resulting in increased
productivity and fewer defects in the components produced [54]. To generate an optimal motion-cueing
algorithm, motion system kinematics is used in order to improve simulator performance in restricting actuator
extensions during coupled movements [55]. In order to enhance the accuracy and efficiency of component
manufacturing utilizing CNC machining operations, optimization processes for machine tool performance and CNC
machining parameters are required [56]. Using online data from the production process, artificial intelligence and
machine learning can make optimization more automated. As a result, the accuracy of machined component and
productivity of part manufacturing can be increased using the optimized machining parameters [57].
To optimize machining conditions and performance, a generalized technique for multi-response machining process
optimization employing machine learning and genetic algorithms is developed [58]. The application of Multi-
Objective evolutionary algorithm during CNC machining operations in order to improve the convergence speed and
performance of part production is shown in the figure 2 [58].

Fig. 2. Data-Driven Multi-Objective evolutionary algorithm Framework in CNC machining optimization [58].
Machine learning is utilized to improve parallel metaheuristics on the shop floor CNC machining operations in
order to increase efficiency during part production processes [59]. Aapplication of machine learning in
optimization process of CNC machine tools is studied to increase component production stability and decrease the
risk of unexpected failure [60]. Response surface approach and machine learning technology are used in order to
optimize cutting settings when turning Ti-6Al-4 V [61]. To optimize machining variables in end milling operations,
the machine learning methodology as the Nelder–Mead simplex method is developed [62]. As a consequence,
optimized machining parameters regarding the flexible conditions and parameters of workpiece and machining
parameters can be obtained using the applications of ML and AI in CNC machining operations to enhance
productivity in process of part production.
5- Cutting tool wear prediction
Machine learning-based technologies is considered an advanced option of tool wear prediction due to its capability
to cope with complicated processes. Due to the non-linear character of tool wear, ANNs are the most preferred
machine learning approach for evaluating wear [63]. To foresee and avoid bad situations for cutting tools and
machinery, modern sensors and computational intelligence are used in order to perform tool condition monitoring
and machine tool diagnostics [64]. The need for building self-sustaining and intelligent autonomous machining
systems prompted the development of cutting tool health monitoring. In recent years, the requirement for tool
condition monitoring or Tool health monitoring has grown in order to enhance lifetime of cutting tools during
machining operations [65]. The strategies for tool condition monitoring are often divided into two categories:
'Offline/Direct methods' and 'Online/Indirect methods.' Direct approaches are most suited for examining and
analyzing complicated failures (hard faults) which are typically unexpected, making them inappropriate for
machine learning [66, 67]. An adaptive neuro-fuzzy inference system can also be used in an online tool system of
wear prediction in turning process in order to provide advanced tool wear monitoring systems [68]. The
procedures of the online tool wear monitoring system in turning operations is presented in figure 3 [68].

Fig. 3. The procedures of the online tool wear monitoring system in turning operations [68].
Deep learning-based tool wear monitoring approach for complicated component milling is implemented to
accurately estimate the tool wear during milling operations [69]. The procedure of the developed methodology in
the tool wear prediction is shown in the figure 4 [69].
Fig. 4. Deep learning-based tool wear monitoring approach for complicated component milling [69].
In the face milling process, a deep neural network as advanced machine learning system is used to automatically
detect tool wear during chip formation process [70]. Drill wear tolerance analysis and optimization is implemented
utilizing an adaptive neuro fuzzy –genetic algorithm approach for long-term usage of cutting tool to maximize
cutting tool life during drilling operations [71]. Advanced neural network systems is developed in order to
accurately predict the cutting tool wear regarding the specific cutting energy during CNC machining operations
[72]. To monitor cutting tool wear in machining operations, simple machine learning combined with data-driven

approaches is developed [73]. Machine learning-based in-situ batch detection of materials during metal cutting
operations is developed to increase the product quality and decrease manufacturing costs [74]. Tool wear
estimation utilizing cloud-based parallel machine learning is developed in order to increase cutting tool life during
machining operations [75].
A comparative study on machine learning algorithms for smart factories is implemented in order to predict the tool
wear during machining operations using random forests [76]. To assess tool wear conditions during milling
operations under a variety of cutting circumstances with a high rate of response, sound waves signals utilizing
advanced machine learning algorithms are used [77]. On a vertical machining center, a machine learning technique
based on the vibration-based multiple network is developed in order to predict cutting tool insert during
machining operations [78]. To predict tool wear progression in the repeated milling process, calibration-based tool
condition monitoring is developed [79]. Tool wear estimation is presented using acoustic emission signals using a
novel machine learning-based methodology in order to accurately predict the condition of cutting tool wear during
milling operations [80]. Machine learning for automated flatness deviation estimation while taking the wear of the
face mill teeth into account is developed to increase accuracy of machine-learning models in tool wear prediction
systems [81]. Artificial neural networks as machine learning system is developed in order to evaluate tool wear on
a modified CNC milling machine [82]. Therefore, cutting tool life during chip formation process of different
materials of workpiece and machining parameters can be analyzed and enhanced using the applications of ML and
AI in prediction process of tool wear in CNC machining operations.
6- Cutting force model
Cutting force is the most important factor in influencing the milling operation's productivity and quality which can
be accurately predicted by using the ML systems [83]. A hybrid force analysis approach in milling operations has
been developed using a machine learning-based simultaneous cutting force model [84]. Modeling framework for
hybrid cutting force model is shown in the figure 5 [84].

Fig. 5. Modeling framework for hybrid cutting force model [84].
A variety of machine learning algorithms, including support vector regression, k-nearest neighbor, polynomial
regression, and random forest, are utilized in order to accurately estimate cutting forces in milling operations. [85].
In high-speed turning operations, machine learning cutting force, surface roughness, and tool life is presented in
order to provide prediction models of cutting forces [86]. A hybrid technique that uses machine learning using the
conventional linear regression method to estimate cutting forces while considering the tool wear conditions is
investigated and developed to accurately predict the cutting forces along machining paths [87]. Wavelet packet
transform analysis of cutting force data for surface texture assessment in CNC turning operations is developed to
remove noise and chatter during chip formation processes [88]. An offline cutting parameters prediction model
related to image representation of cutter workpiece contact geometry is developed using a neuro-physical learning
approach in order to increase prediction accuracy in varied cutting situations [89]. To improve the accuracy of
cutting force modeling systems, a machine learning-calibrated smart tool holder for measuring cutting force in
precise turning operations of S15C low carbon steel has been created [90]. Using real-time cutting force
measurements and a CNN approach as machine learning system, online tool wear categorization during dry
machining operations is developed [91]. Artificial Neural with signal spectrum image analysis using the cutting
force prediction systems is developed to determine the cutting tool's amount of damage during machining
operations [92]. Thus, accuracy as well as flexibility of cutting force models during different conditions of CNC
machining operations are developed using the applications of ML and AI in cutting force perdition methodologies.
7- CNC Machine tool maintenance
The CNC machine tool maintenance process always needs time and money. Accurate prediction of calibration,
component modifications, and service of CNC machine tools is one of the most difficult aspects and challenges of
running a CNC machine tool [93]. Machine learning and artificial intelligence are closely tied to machine tool
maintenance, advancing prediction and preventative approaches aimed at lowering downtime and improving
productivity [94]. Machine learning can accurately predict when machine tools need to be serviced and present
the optimal time to repair the machine tools in order to minimize the time and cost of CNC Machine tool
maintenance [95]. Predictive machine tool maintenance procedures may be done accurately when a machine is
driven by machine time and condition data and operators get real-time streams of data feedback. Automatic
warnings can be applied when a machine tool needs to be maintained, a part replaced, or a function corrected
before it breaks down, in order to provide stable workflow in machine tool and smoothly keep production process
running in process of part production using CNC machine tools [96]. So, cause-and-effect links can be created using
the connections of artificial intelligence and CNC machine tools. As a consequence, more information and better
decision-making for CNC machine tool production processes can be generated, in order to increase added values in
process of CNC machine tool component manufacturing [97]. A hybrid predictive maintenance approach for CNC
machine tool driven by digital twin is presented in order to provide accurate prediction methodologies during
process of part production using CNC machine tools [98]. Developed method of maintenance approach for CNC
machine tool is shown in the figure 6 [98].

Fig. 6. Developed method of maintenance approach for CNC machine [98].
Advanced machine learning systems is developed to evaluate the maintenance operations including tool wear
monitoring in the CNC machine tools [95]. To monitor data in assessing CNC machine tool and cutting process
conditions, advanced machine learning system is developed [99]. A tool health monitoring system is created using
machine learning techniques in end milling process in order to increase cutting too life and enhance efficiency of
part production [100]. Thus, advanced procedures of CNC machine tool maintenance can be obtained as a result
of applying the ML and AI to the working time of CNC machine tools during process of part production.
8- Monitoring of machining operations
The application of machine learning in health monitoring of CNC machine tools is recently developed in an era of
artificial intelligence systems in order to enhance efficiency in part production using machining operations [101].
Condition monitoring systems is an essential step in maintenance of CNC machine tools in order to keep the CNC
machining operations safe and reliable [102]. A cyber-physical manufacturing and engineering structure is
presented in order to provide a smart monitoring system for CNC cutting tools [103]. A combination of physical
and virtual modeling of the milling process in the smart CNC machine monitoring system is generated which is
shown in the figure 7 [103].

Fig. 7. A combination of physical and virtual modeling of the milling process in the smart CNC machine monitoring
system [103].
To monitor and obtain the performances of CNC machine tools during part production processes, advanced
decision making application is presented [93]. By using advanced machine learning system, performance
monitoring and the impact of process parameters such as cutter speed, feed rate and depth of cut on outputs in
turn-milling operations are studied [104]. Six rotating sensors on joints of three legs are used to solve forward
kinematics in the Stewart structure in order to increase accuracy during the movement of Stewart structure [105].
Monitoring of CNC machining operations using adaptive neuro-fuzzy integration of multi-sensor signals is
implemented in order to prevent and detect the cutting tool errors during machining operations [106]. To enhance
accuracy of CNC machining operations, method of machining processes monitoring using virtual reality and a
digitized twin systems is developed [107].
Planning and optimization of machining parameters is developed using the online monitoring systems the for AISI
P20 removal rate while milling operations to minimize total manufacturing time and boost material removal rate
during machining operations [108]. To boost productivity during machining operations of tough to cut materials,
machine learning approaches such as decision trees, artificial neural networks, and support vector machines are
examined for chatter predictions in titanium alloy (Ti-6Al-4V) high-speed milling [109]. In-process tool wear
prediction system based on machine learning techniques and force analysis regarding the speed of spindle and
feed rate machining parameters is developed to obtain the flank wear during machining operations [110].
Response surface technique incorporating desirability function and genetic algorithm approach is developed in
order to obtain the CNC machining parameter optimization [111]. To enhance the capabilities and accuracy of
machine tool monitoring systems, applications of artificial neural network is presented [112]. As a result, the
process of obtaining and analyzing the data through monitoring of machining operations are developed by using
the ML and AI in the advanced monitoring and decision making in computer aided process planning systems.
9- Surface quality prediction
Surface roughness is a critical metric for assessing the quality of produced products. Advanced machining
procedures aim to produce parts with high geometrical accuracy and enhanced surface finishes while lowering the
cost of final products. As a result, certain traditional machining techniques are unable to meet the industrial

requirements, necessitating the use of a post-machining surface finishing process to obtain a high-quality surface
finish [113]. One of the most important grading standards for product quality is surface roughness. Surface
roughness of machined parts can be minimized in order to enhance working life of produced parts [114]. To
predict and analyze surface finish of machined components, Neural Networks by using the advanced AI systems is
used [115]. Applications of machine learning algorithms in prediction of surface roughness characteristics are
developed in order to accurately anticipate surface quality of machined components utilizing turning operations
[116]. Linear regression, random forest and decision tree as advanced machine learning systems is applied in order
to predict the surface quality of machined parts [117]. Machining accuracy and surface quality for CNC machine
tools is predicted using data driven approach in order to accurately predict surface roughness in machining
operations [118]. To predict surface roughness in machining operations, application of deep learning neural
network using vibration signal analysis is studied [119]. The developed methodology of study in application of AL in
surface roughness prediction of machined parts is shown in figure 8 [119].
Fig. 8. Application of AL in surface roughness prediction of machined parts [119].
To increase accuracy and reliability in terms of surface quality enhancement of machined components,
autonomous surface roughness prediction based on wear of face mill teeth is developed [120]. Neural network
analysis as multi-layer perceptron model and a radial basis function model is developed to predict the and surface
roughness in aluminum alloy machining operations [121]. Machine learning was used to analyze cutting forces in
the helical ball end milling process in order to provide advanced methodology in cutting forces calculation [122].

Surface roughness measuring systems on-machine and in-process for precise production is developed in order to
increase surface quality of machined components [123]. Advanced surface metrology system in a manufacturing
line is illustrated in the figure 9 [123].
Fig. 9. Advanced surface metrology system in a manufacturing line [123].
Machine learning algorithms based on a sensory milling machine tool for real-time monitoring and evaluation of
surface roughness have been developed to enhance surface quality of machined components [124]. Multimodal
data-driven hybrid machine learning is developed in order to provide condition prediction of cutting tool using
advanced machine learning system, [125]. Deep learning-based tool wear detection system is developed utilizing
multi-scale feature fusion and a channel attention mechanism in order to enhance cutting tool life [126]. To
provide advanced method of surface roughness prediction in machined parts, a nested-ANN model using the
impacts of cutting forces and tool oscillations is developed [127]. As a result, surface quality of machined parts can
be enhanced using the applications of ML and AI in surface prediction of machined components using CNC
machine tools in order to enhance productivity of CNC matching operations.
10- Energy prediction systems
Due importance of decreasing energy waste during industrial production, building energy perdition and
management systems are considered in different research works [128, 129]. Machine learning techniques are
recently used in prediction models of energy consumption during machining operations. The accuracy, durability,
and precision of traditional time series forecasting methods, as well as their generalization capacity, are greatly
improved by using th