Intelligent Machining Process Research Articles

Investigation on universal tool wear measurement technique using image-based cross-correlation analysis

Early detection of tool defects enables proactive prevention of disruption, thus increasing productivity, maintaining quality and agility that brings significant competitive value to the organization. Hence, an effective tool wear monitoring system is vital for intelligent machining process. With the aim to develop an on-machine universal offline monitoring system, a novel quantitative image-based tool wear measurement system based on cross correlation analysis, is proposed to measure tool wear directly from the machining workbench. The sensitivity and accuracy of the proposed technique were further improved through cross-covariance analysis of original and worn tool images. Analyses on various wear conditions of drill bit, end mill, taper tap and carbide insert demonstrated the high effectiveness of the developed measurement system, reflected in the cross-correlation graphs pattern with wear measurement at a microscale down to 100 µm. The cross-correlation based measurement enables optimization of the machining productivity through just-in-time tool change through effective monitoring technique.

An effective retrieval approach of 3D CAD models for macro process reuse

With the increasing of the process data, process data-driven intelligent machining process planning is becoming more and more important in manufacturing industries. In the process data, the macro process contains abundant process design intent, which has important reuse value. However, existing 3D CAD model retrieval methods for macro process reuse are mainly on the premise of geometric similarity, which make them difficult to guarantee the reusability of the macro process associated with the similar results. In this paper, an effective retrieval approach of 3D CAD models for macro process reuse is presented. First, a process skeleton model is introduced to guide the structuralization of process data based on the macro process of existing parts. Then, a probability statistics approach is presented to map machining features of query part onto the macro process of existing part. Finally, process design intent-driven accessible machining region extraction is proposed, and then the part similarity assessment model based on the machining region is established to calculate the macro process similarity between query part and existing part. A prototype system has been developed to verify the effectiveness of the proposed approach.

The wear performance of carbide tools coated with TiAlSiN, AlCrN and TiAlN ceramic films in intelligent machining process

Nitride-based coatings are applied by cathodic arc physical vapor deposition (CAPVD) to improve the tribological properties of cutting tools. The present study examines the tool life of carbide tools coated with TiAlSiN, AlCrN and TiAlN films in intelligent machining process. Coating process was applied on both prismatic carbide test specimens and solid carbide end mills. Coating characterization was carried out on the test specimens. The structural, mechanical and tribological properties of different nitride-based coatings were investigated by means of field emission scanning electron microscope (FEG-SEM), X-ray diffractometer (XRD), scratch tester, reciprocating tribometer, calotester, microhardness device and optical profilometer. Impax steel was machined in CNC vertical machining center with uncoated and coated carbide end mills in order to determine the actual operating performance of the coatings. The g codes and toolpaths were created in the SolidCAM iMachining software. The cutting speed, feeds and overlap values are selected automatically and variably depending on geometry, tool and workpiece materials. The flank wear widths of tools were determined by SEM. In addition, the surface roughness values of the impax steel were measured from the finish surfaces. According to the scratch test results, the best adhesion results were obtained for TiAlN coating and the Lc1 critical load value was determined as about 30 N. The reciprocating sliding test results showed that the highest wear rate was obtained for the TiAlSiN coated specimen and the lowest wear rate was obtained for the uncoated specimen. Flank wear was observed on the tools after the milling process and the highest wear resistance was obtained TiAlN coated end mill. The lowest surface roughness value was obtained from the surface of impax steel workpiece which was milled with carbide end mill coated with TiAlN ceramic film.

An effective adaptive dynamic evolution computing approach of roughing process for part with complex pockets

With the increasing of the machining process data, machining process data-driven intelligent machining process planning is becoming more and more important in manufacturing industries. However, existing methods mainly focus on searching the similar NC processes for reference by designers, and the reuse process relies heavily on the experience and knowledge of designers, requiring significant human interactions. In this paper, a novel adaptive dynamic evolution computing approach of roughing process for part with complex pockets is proposed to reduce the burden of designers and improve the efficiency of NC programming. A locally inscribed circle (LIC) moving frame is established to guide the calculation of machining region (MR) and undercut region (UR) for complex pocket in roughing and to circumvent the self-intersection detection issue of whole feature contour offset, and the URs are categorized by the topological structure of its medial axis (MA) for roughing preliminary process scheme adaption. Roughing process adaptive evolution mechanism, including vertical and horizontal adaption, is explored to ensure the connectivity of roughing process context. Process design intent-driven decision-making for roughing process adaptive evolution is proposed to make up the deficiency from the geometric analysis perspective. A prototype system based on CATIA has been developed to verify the effectiveness of the proposed approach.

A novel integrated tool condition monitoring system

A tool condition monitoring (TCM) system is vital for the intelligent machining process. However, literature has mostly ignored the interaction effect between product quality and tool degradation and has devoted less attention to the criterion of integrated diagnostics and prognostics to cutting tools. In this paper, we aim to bridge the gap and make an attempt to propose a novel integrated tool condition monitoring system based on the relationship between product quality and tool degradation. First, a cost efficient experimentation concerning high-speed CNC milling machining was implemented. Subsequently, a comprehensive correlation investigation was performed; revealing strong positive relationship exists between product quality and tool degradation. Mapping this relationship, an integrated TCM system pertaining to diagnostics and prognostics was proposed. Herein, the diagnostic reliability was enhanced by researching on the use of a multi-level categorization of degradation. The prognostic competence was enhanced by formulating it explicitly for the tools critical zone as a function of tool life. The system is integrated in a manner that, whenever the degradation curve of the tool reaches the critical zone, prognostics module is triggered, and remaining useful life is assessed instantaneously. To enhance the performance of this system, it is modeled employing support vector machine with optimal training technique. The proposed system was validated based on the experimental data. An extensive performance investigation showed that the proposed system provides a robust problem-solving framework for the intelligent machining process.

An effective freeform surface retrieval approach for potential machining process reuse

With the increasing of the machining process data, which are the direct and effective carrier of knowledge, intelligence and experience of skilled engineers, machining process data-driven intelligent machining process planning is becoming more and more important in manufacturing industries. One of the key technologies is to retrieve the similar geometry with machining process reuse value in a fine manner. However, existing 3D CAD model retrieval methods for manufacturing reuse mainly focus on the parts composed of non-freeform surface features machined with 2 1/2-axis CNC milling, while the parts including complex freeform surfaces accounted for a large proportion are little involved. In this paper, a novel freeform surface retrieval approach for potential machining process reuse is presented. First, similar tensor field pattern freeform surface feature is introduced to represent the complex freeform surface into structured freeform surface model. Then, freeform surface content code for accelerating freeform surface retrieval is given to filter out unmatched freeform surfaces efficiently. Moreover, the principal pathline indicating the overall evolution trend of feature pathlines is extracted and represented using D2 shape descriptor to establish the feature similarity assessment model. Finally, sub-graph isomorphism-based matched feature pairs extraction algorithm is presented to calculate the similarity between matched freeform surfaces. A prototype system based on CATIA has been developed to verify the effectiveness of the proposed approach.

Integrated optimization methodology for intelligent machining of inconel 825 and its shop-floor application

The machining optimization is one of the most essential tasks for economic production of components in manufacturing industries. The intelligent machining process aims to produce the components for desired surface quality at minimum machining time∕cost. The innovative aspect of this work is the development of an integrated optimization methodology used for optimizing the process parameters in machining Inconel 825 aerospace alloy. Turning experiments have been conducted with spindle speed (N), feed rate (f), and depth of cut (d) that are considered as process parameters and the centre line average value of surface roughness (R a) as response. The experimental study shows that R a is influenced by spindle speed followed by feed rate. An artificial neural network (ANN) model has been developed for predicting R a. The ANN architecture having 3–12–1 is found to be optimum network and model predicts unseen data sets with an average percentage error of 6.51 %. The predictive model is integrated with particle swarm optimization (PSO) approach to optimize the process parameters for desired surface roughness of jobs to be produced at minimum time. The robustness of the method shows its superiority and taken less than ten iterations. For shop-floor implementation of the approach, MATLAB-GUI (graphical user interface)-based interactive screens are developed that help the machine tool operator to obtain optimum process parameters.

Cutting force-based adaptive neuro-fuzzy approach for accurate surface roughness prediction in end milling operation for intelligent machining

End milling is one of the most common metal removal operations encountered in industrial processes. Product quality is a critical issue as it plays a vital role in how products perform and is also a factor with great influence on manufacturing cost. Surface roughness usually serves as an indicator of product quality. During cutting, surface roughness measurement is impossible as the cutting tool is engaged with the workpiece, chip and cutting fluid. However, cutting force measurement is easier and could be used as an indirect parameter to predict surface roughness. In this research work, a correlation analysis was initially performed to determine the degree of association between cutting parameters (speed, feed rate, and depth of cut) and cutting force and surface roughness using adaptive neuro-fuzzy inference system (ANFIS) modeling. Furthermore, the cutting force values were employed to develop an ANFIS model for accurate surface roughness prediction in CNC end milling. This model provided good prediction accuracy (96.65 % average accuracy) of surface roughness, indicating that the ANFIS model can accurately predict surface roughness during cutting using the cutting force signal in the intelligent machining process to achieve the required product quality and productivity.

An Enabling Digital Foundation Towards Smart Machining

Today's major challenges for manufacturing companies in the aerospace and automotive industries are clear: global cooperation with multiple supply chain partners, production optimization, management and tracking of information so as to meet new requirements in terms of traceability, security and sustainability. The need for a data exchange standard that allows disparate entities and their associated devices in a manufacturing system to share data seamlessly is clearly obvious. And the first expected impact is the ‘next generation’ smart controller that could really enable an intelligent machining process based on real-time monitoring and diagnosis, self-learning decision and adaptive optimization. The four-year project titled FoFdation envisions a ‘Digital and Smart Factory’ architecture and implementation. This has the potential to achieve significant benefits in earlier visibility of manufacturing issues, faster production ramp-up time, faster time to volume production and subsequently shorter time to market, reduced manufacturing costs and improved product quality, as well as sustainability objectives like low energy consumption and waste reduction. The present paper describes the on-going work with specific focus on the definition and implementation of the FoFdation Smart Machine Controller (SMC) in an adaptable architecture that satisfies both commercial and open source CNC controllers. It highlights the project's end use validation framework as well as sets a strong Manufacturing Information System foundation on which process optimization and control as well as sustainable practices can be based. It presents the general vision of the target solution for the SMC developed in the FoFdation project. It is based on efforts past and present both by academia and industry in various capacities and proposes tentative implementations based on the STEP-NC standard to define the machine controller of the future.