Manufacturing organizations need to use different kinds of techniques and tools in order to fulfill their foundation goals. In this aspect, using machine learning (ML) and data mining (DM) techniques and tools could be very helpful for dealing with challenges in manufacturing. Therefore, in this paper, a comprehensive literature review is presented to provide an overview of how machine learning techniques can be applied to realize manufacturing mechanisms with intelligent actions. Furthermore, it points to several significant research questions that are unanswered in the recent literature having the same target. Our survey aims to provide researchers with a solid understanding of the main approaches and algorithms used to improve manufacturing processes over the past two decades. It presents the previous ML studies and recent advances in manufacturing by grouping them under four main subjects: scheduling, monitoring, quality, and failure. It comprehensively discusses existing solutions in manufacturing according to various aspects, including tasks (i.e., clustering, classification, regression), algorithms (i.e., support vector machine, neural network), learning types (i.e., ensemble learning, deep learning), and performance metrics (i.e., accuracy, mean absolute error). Furthermore, the main steps of knowledge discovery in databases (KDD) process to be followed in manufacturing applications are explained in detail. In addition, some statistics about the current state are also given from different perspectives. Besides, it explains the advantages of using machine learning techniques in manufacturing, expresses the ways to overcome certain challenges, and offers some possible further research directions.

Machine learning and data mining in manufacturing

This paper provides a literature review on zero defect manufacturing based on the content analysis performed for 280 research articles published from 1987 to 2018 in a variety of academic journals ...

Zero defect manufacturing: state-of-the-art review, shortcomings and future directions in research

Machine learning in tolerancing for additive manufacturing

The adoption of laser powder bed fusion (L-PBF) for metals by the industry has been limited despite the significant progress made in the development of the process chain. One of the key obstacles i...

Perspectives of using machine learning in laser powder bed fusion for metal additive manufacturing

https://opus.lib.uts.edu.au/bitstream/10453/147577/2/1-s2.0-S1474034620300707-main.pdf

Predictive model-based quality inspection using Machine Learning and Edge Cloud Computing

Tolerance analysis aims on checking whether specified tolerances enable functional and assembly requirements The tolerance analysis approaches discussed in literature are generally assumed without the consideration of parts’ form defects This paper presents a new model to consider the form defects in an assembly simulation A Metric Modal Decomposition (MMD) method is henceforth, developed to model the form defects of various parts in a mechanism The assemblies including form defects are further
assessed using mathematical optimization The optimization involves two models of surfaces: real model and difference surface-base method, and introduces the concept of signed distance The optimization algorithms are then compared in terms of time consumption and accuracy To illustrate the methods and their respective applications, a simplified over-constrained industrial mechanism in three dimensions is also used as a case study

/pdf/tolerance-analysis-form-defects-modeling-and-simulation-by-32leteimwa.pdf

Tolerance analysis — Form defects modeling and simulation by modal decomposition and optimization

Geometrical variations management for additive manufactured product

In many modern manufacturing industries, data that characterize the manufacturing process are electronically collected and stored in databases. Due to advances in data collection systems and analysis tools, data mining (DM) has widely been applied for quality assessment (QA) in manufacturing industries. In DM, the choice of technique to be used in analyzing a dataset and assessing the quality depend on the understanding of the analyst. On the other hand, with the advent of improved and efficient prediction techniques, there is a need for an analyst to know which tool performs better for a particular type of dataset. Although a few review papers have recently been published to discuss DM applications in manufacturing for QA, this paper provides an extensive review to investigate the application of a special DM technique, namely support vector machine (SVM) to deal with QA problems. This review provides a comprehensive analysis of the literature from various points of view as DM concepts, data preprocessing, DM applications for each quality task, SVM preliminaries, and application results. Summary tables and figures are also provided besides to the analyses. Finally, conclusions and future research directions are provided.

/pdf/review-of-data-mining-applications-for-quality-assessment-in-2e3k29yprs.pdf

Review of data mining applications for quality assessment in manufacturing industry: support vector machines

To determine the relative position of any two surfaces in a system, one approach is to use operations (Minkowski sum and intersection) on sets of constraints. These constraints are made compliant with half-spaces of R n where each set of half-spaces defines an operand polyhedron. These operands are generally unbounded due to the inclusion of degrees of invariance for surfaces and degrees of freedom for joints defining theoretically unlimited displacements. To solve operations on operands, Minkowski sums in particular, "cap" half-spaces are added to each polyhedron to make it compliant with a polytope which is by definition a bounded polyhedron. The difficulty of this method lies in controlling the influence of these additional half-spaces on the topology of polytopes calculated by sum or intersection. This is necessary to validate the geometric tolerances that ensure the compliance of a mechanical system in terms of functional requirements. In tolerance analysis, sets of constraints can be compliant with operand polyhedra.These operands are generally unbounded due to the inclusion of degrees of freedom.Cap half-spaces are added to each polyhedron to make it compliant with a polytope.The influence of the cap half-spaces on the topology of polytopes must be controlled.It is necessary to ensure the compliance of a mechanism in terms of requirements.

https://hal.archives-ouvertes.fr/hal-01202482/document

Tolerance analysis by polytopes

Reconfigurable manufacturing systems constitute a new manufacturing paradigm and are considered as the future of manufacturing because of their changeable and flexible nature. In a reconfigurable manufacturing environment, basic modules can be rearranged, interchanged, or modified, to adjust the production capacity according to production requirements. Reconfigurable machine tools have modular structure comprising of basic and auxiliary modules that aid in modifying the functionality of a manufacturing system. As the product’s design and its manufacturing capabilities are closely related, the manufacturing system is desired to be customizable to cater for all the design changes. Moreover, the performance of a manufacturing system lies in a set of planning and scheduling data incorporated with the machining capabilities keeping in view the market demands. This research work is based on the co-evolution of process planning and machine configurations in which optimal machine capabilities are generated through the application of multi-objective genetic algorithms. Furthermore, based on these capabilities, the system is tested for reconfiguration in case of production changeovers. Since, in a reconfigurable environment, the same machine can be used to perform different tasks depending on the required configuration, the subject research work assigns optimum number of machines by minimizing the machining capabilities to carry out different operations in order to streamline production responses. An algorithm has also been developed and verified on a part family. As a result of the proposed methodology, an optimized reconfigurable framework can be achieved to realize optimal production of a part family. Finally, the proposed methodology was applied on a case study and respective conclusions were drawn.

/pdf/optimum-machine-capabilities-for-reconfigurable-1yfy17yhrq.pdf

Lazhar Homri

Papers

Tolerance analysis — Form defects modeling and simulation by modal decomposition and optimization

Geometrical variations management for additive manufactured product

Review of data mining applications for quality assessment in manufacturing industry: support vector machines

Tolerance analysis by polytopes

Optimum machine capabilities for reconfigurable manufacturing systems