Naeem Ullah Dar

A fuzzy expert system for optimizing parameters and predicting performance measures in hard-milling process

The main focus of research in hard-milling domain has been the enhancement of tool life and the improvement in workpiece surface quality. This paper deals with the application of expert system technology in order to use the experimental data for optimization of milling parameters so as to achieve targets of enhancing tool life and improving workpiece surface finish. Hard-milling experiments were conducted to study the effects of workpiece material hardness, cutters helix angle, milling orientation and coolant upon tool life, workpiece surface roughness, and cutting forces. The experimental data were converted to useful information using ANOVA and numeric optimization, and this information was used to develop the knowledge-base in form of IF-THEN rules. Expert system utilized fuzzy logic for its reasoning mechanism, while, fuzzy data sets and crisp sets were freely mixed in antecedents and consequents of the rules. Effectiveness of the expert system was based upon two modules, namely optimization module and prediction module, with each of them operating upon different set of rules. Optimization module provides the optimal selection and combination of aforementioned milling parameters according to the desired objective, while the prediction module provides the prediction of performance measures for the combination of parameters finalized by the optimization module.

Comparison of fuzzy expert system based strategies of offline and online estimation of flank wear in hard milling process

Accurate estimation of flank wear during any in-progress machining process is highly important for the purpose of controlling product quality and the production rate. Hard milling is among few of the recently popularized technologies of metal cutting domain and is found under intense research for the purpose of estimation and control of tool wear. In the presented paper two fuzzy rules based strategies are explained and compared for accurate estimation of tools flank wear in hard milling process. The offline strategy uses length of cut (LoC) as major input besides tool helix angle and workpiece material hardness, while for the online strategy LoC is replaced with the cutting force. Series of hard milling experiments were performed in order to obtain data for the development of two fuzzy expert systems as well as for testing of both of the strategies. ANOVA showed LoC and cutting force were more significant than other input parameters for the estimation of flank wear, and the design of fuzzy sets for input parameters was based upon this analysis. Two expert systems were tested using experimental data and the results showed that online strategy was 67.9% more accurate than offline one in estimating flank wear.

Optimizing cutting parameters in minimum quantity of lubrication milling of hardened cold work tool steel

Abstract Despite the numerous advantages offered by high-speed and high-performance cutting technologies, the issue of diminished tool life still remains profoundly concerning, especially in the case of machining hardened steels. Moreover, in finish machining, the requirement of improving workpiece surface finish also gains considerable importance. Application of the minimum quantity of lubrication (MQL) has delivered so many benefits that it has almost become part and parcel of turning, drilling, and milling technologies. In this research work, the high-speed milling of hardened cold work tool steel (62 HRc), under an MQL environment, was experimentally investigated and a response surface methodology was utilized to optimize the cutting parameters. A series of experiments was performed in order to quantify the effects of following three cutting parameters on tool life and arithmetic average surface roughness: cutting speed (Vc), feed rate (fz), and radial depth of cut (ae). The surface roughness was measured in two directions: along the feed, Ra, and along the pick-feed, Ra(pick). Analysis of variance (ANOVA) performed on the data revealed that the effect of cutting speed was significant on tool life as well as on Ra. Moreover, the effects of feed rate and radial depth of cut on tool life and Ra(pick) respectively were found to be significant. Scanning electron microscopy (SEM) and energy dispersive spectrometry (EDS) analyses were performed to determine the dependence of different tool damage modes on levels of cutting parameters utilized. It was found that chipping and adhesion were the dominant tool damage modes in most of the experimental runs and their severity was dependent on levels of feed rate and cutting speed respectively.

Self-developing fuzzy expert system: a novel learning approach, fitting for manufacturing domain

The foremost challenge faced by expert systems, for their applicability to real world problems, is their inherent deficiency of dynamism. For an expert system to be more pragmatic and applicable, the whole structure of an expert system—including rule-base, fuzzy sets, and even user-interface—needs to be upgraded continuously. This continuous up gradation demands full-time, repetitive, and cumbersome involvement of knowledge engineers. Machine learning is an answer to this problem, but unfortunately, the solutions that have been provided are limited in scope. For example, most of the researchers put forward techniques of either generating just rules from data, or self-expanding and self-correcting knowledge-base only. The innovative approach presented in this paper is broader in scope. It enhances the efficacy and viability of expert systems to be more capable of coping with dynamic and ever-changing industrial environments. The objective is facilitated by rendering, concurrently, the self-learning, self-correcting, and self-expanding abilities to the expert system, without requiring knowledge engineering skills of the developers. This means that the user needs just to feed data in form of the values of input/output variables and the complete development of expert system is done automatically. The superiority of the proposed expert system, regarding its continuous self-development, has been explained with the help of three examples related to prediction and optimization of milling and welding processes.

Numerical simulation and experimental verification of CMOD in SENT specimen: Application on FCGR of welded tool steel

Single-edged notched tension (SENT) specimen is used to study the fatigue crack growth rate (FCGR) behavior of AISI 50100 steel using MTS 810. Calibration tests are run to get plots of crack mouth opening displacement (CMOD) vs. load and CMOD vs. crack length-to-width ratio with the known crack lengths. Numerical simulation is also done to try to establish a relation between crack length and CMOD. FCGR of welded and un-welded specimens are plotted against stress intensity factor range to show the effect of welding on fatigue crack growth rate of AISI 50100 steel. The experimentally obtained CMOD values are compared with values obtained by numerical simulation using ABAQUS/Standard™ software package. Results show that numerical values are in good agreement with experimental data for small crack lengths and lower values of applied load.

Optimal formation of fuzzy rule-base for predicting process's performance measures

Research highlights? Fuzzy rule-base can model a complex manufacturing process. ? Simulated annealing algorithm can optimize fuzzy rule-base formation. ? Change in shape of fuzzy sets causes minor improvement in estimation accuracy. For various physical processes, especially those demanding high cost or operational time, it becomes crucial to have accurate predictions of their key performance measures based on given settings of different input parameters. Among other artificial intelligence based tools, fuzzy rule-based systems have also been widely used for this purpose. Widespread applicability of the rule-based systems has been restricted by lack of accuracy in the prediction results and inherent difficulties in different approaches that have been utilized for improving their prediction capabilities. The paper presents a two-stage approach for enhancing accuracy of prediction results. The first stage seeks best possible assignment of fuzzy sets of a response variable to the rules of a fuzzy rule-base, while the second stage looks for further improvement by adjusting shapes of the fuzzy sets of the response variable. For accomplishment of both of the stages, simulated annealing algorithm has been utilized and the approach has been practically applied on experimental data related to a turning process. The process has resulted in development of a rule-base that predicts with highly acceptable levels of accuracy.

Analysis of circumferentially welded thin-walled cylinders to investigate the effects of varying clamping conditions:

Abstract Arc fusion welding predominates in the welding industry as a reliable joining method and has been the subject of investigations by researchers for decades. To ensure in-service structural integrity, optimization of weld-induced imperfections such as welding deformations and residual stresses is critically desirable in circumferentially welded thin-walled cylinders owing to their wide applications in aerospace and aeronautical structures, pressure vessels, and nuclear engineering fields. In this research, computational methodologies for sequentially coupled non-linear transient thermomechanical analysis of the complex arc welding of thin-walled cylinders of stainless steel (AISI 304) are presented. Detailed three-dimensional finite element (FE) simulations with a single V butt-weld joint configuration of 150 mm outer diameter and 3 mm wall thickness cylinders are carried out to investigate the effects of varying structural boundary conditions (mechanical constraints) on weld-induced distortions and residual stress fields. Basic FE models are validated with carefully recorded and properly instrumented experimental data for temperature distribution, deformations, and residual stresses. Predicted and measured welding distortions and residual stresses are compared and discussed in detail. The results reveal that axial deformations are strongly dependent on the degree of restraints. Low-restraint structures exhibit high axial shrinkage, and vice versa. Diametral/radial shrinkage for different clamping conditions show no significant variation. Further, residual stresses show a weak dependence on the degree of restraints. Although the stress levels slightly vary in magnitude, a similar trend is observed for all the structural clamping conditions studied.

An Investigation into the Fatigue Crack Growth Rate of Electron Beam-Welded H13 Tool Steel: Effect of Welding and Post-Weld Heat Treatment

Fatigue crack growth rate (FCGR) behavior of 3-point bend specimen of electron beam-welded AISI H13 tool steel is studied. Three types of specimens were studied here; specifically: the base metal, as-welded, and post-heat-treated welded samples. The crack length is measured visually as well as calculated using crack mouth opening displacement (CMOD) gage. The FCGR curves of different specimens are compared. The validity of using CMOD as a tool for indirect crack length measurement as per ASTM E399 is explored. Additionally, the possibility of using CMOD as a crack driving force parameter instead of stress intensity range (ΔK) is explored. It is shown that the CMOD is a better crack driving force parameter and the indirect crack length measurement is not a reliable tool, especially for welded specimens. In the end, CMOD versus crack length is numerically simulated by finite element analysis to give us a base line CMOD versus crack length without microstructural or plasticity effects.

Residual Stress Fields due to Varying Tack Welds Orientation in Circumferentially Welded Thin-Walled Cylinders

The local, nonuniform heating and subsequent cooling during the welding processes causes complex thermal stress/strain fields to develop that finally leads to residual stresses, distortions, and their adverse consequences. Residual stresses are of prime concern to the industries producing weld-integrated structures around the globe because of their obvious potential to cause dimensional instability in welded structures, contribute to premature fracture/failure, along with the significant reduction in fatigue strength and in-service performance of the welded structures. Arc welding with single or multiple weld runs is an appropriate and cost effective joining method to produce high-strength structures in these industries. A multifield interaction in arc welding process makes it a complex manufacturing process. A number of geometric and process parameters are contributing to significant stress levels in arc-welded structures. In the present analysis, parametric studies are conducted for the effects of a critical geometric parameter, that is, tack weld on the corresponding residual stress fields in circumferentially welded thin-walled cylinders. Tack welds offer a considerable resistance to the shrinkage and the orientation, and size of tacks can alter altogether the stress patterns within the weldments. Hence, a critical analysis for the effects of tack weld orientation is desirable.

Residual Stress Fields Under Different Clamping Conditions in Circumferentially Welded Thin-Walled Cylinders

Arc welding is a reliable joining method widely utilized in nuclear, pressure vessels, aerospace and aeronautical structures to ensure the intended in service behaviour during the thermal and/or pressure loadings. Weld induced deformations and high residual stresses often occur during the course of welding. These cause significant threats for the structural integrity of the nuclear power plant components, particularly in stress corrosion inhibited environments owing to the risk of stress corrosion cracking (SCC). In this research, the consequences of five different structural boundary conditions on the evolution of residual stress fields after the welding are investigated. Both experimental and numerical simulations based on finite element modeling are employed during the course of investigation. Full three-dimensional FE models for the circumferentially, arc welded thin-walled cylinders are developed in ANSYS® . The complex coupled, thermo-mechanical phenomenon during the welding is simulated by sequentially coupled approach enhanced by user written APDL subroutines. The role of welding restraints in minimizing / optimizing the residual stresses is presented and discussed in detail. The result reveals that residual stresses show weak dependence on the degree of the restraints. Although the stress levels slightly varies in magnitude, but similar trend is observed for all the structural clamping conditions under study. Simulation results validated through full-scale experiments with high-tech reliably instrumented welding and measuring equipments shows promising features of the developed modelling and simulation strategy for use in shop floor applications.© 2008 ASME